WO2022048595A1 - Speech-to-text auto-scaling for live use cases - Google Patents

Speech-to-text auto-scaling for live use cases Download PDF

Info

Publication number
WO2022048595A1
WO2022048595A1 PCT/CN2021/116202 CN2021116202W WO2022048595A1 WO 2022048595 A1 WO2022048595 A1 WO 2022048595A1 CN 2021116202 W CN2021116202 W CN 2021116202W WO 2022048595 A1 WO2022048595 A1 WO 2022048595A1
Authority
WO
WIPO (PCT)
Prior art keywords
deltas
current values
latency
computational resources
latency threshold
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/116202
Other languages
English (en)
French (fr)
Inventor
Daniel BOLANOS
Antonio Rogelio Lee
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
IBM China Co Ltd
International Business Machines Corp
Original Assignee
IBM China Co Ltd
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by IBM China Co Ltd, International Business Machines Corp filed Critical IBM China Co Ltd
Priority to JP2023514502A priority Critical patent/JP7748783B2/ja
Priority to GB2304504.0A priority patent/GB2614179A/en
Priority to DE112021003525.8T priority patent/DE112021003525B4/de
Priority to CN202180053854.4A priority patent/CN116194987B/zh
Publication of WO2022048595A1 publication Critical patent/WO2022048595A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5022—Mechanisms to release resources
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/285—Memory allocation or algorithm optimisation to reduce hardware requirements
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/501—Performance criteria

Definitions

  • the present invention relates generally to the field of computing, and more particularly to a speech-to-text auto-scaling system.
  • Speech-to-Text relates to the field of transcribing words into textual form based on spoken language.
  • Real use cases may include, but are not limited to, closed-captioning, automated agents, and dictation.
  • a natural and smooth interaction between a user and a cloud-based speech-to-text service is desired.
  • Live interaction between the user and the cloud-based speech-to-text service requires fast and efficient delivery of recognition transcripts by a speech recognition engine.
  • CPU central processing unit
  • a method, computer system, and computer program product for speech-to-text auto-scaling of computational resources may include computing a delta for each word in a transcript.
  • the computed delta may be for each word in a transcript between a wall clock time and a time when the word is delivered to a client.
  • the embodiment may also include submitting the deltas to a group of metrics servers, where the metrics servers are configured to collect the deltas.
  • the embodiment may further include requesting from the group of metrics servers current values of the deltas.
  • the embodiment may also include determining whether the current values of the deltas exceed a pre-defined max-latency threshold.
  • the embodiment may further include adjusting the allocated computational resources based on a frequency of the current values of the deltas that exceed the pre-defined max-latency threshold.
  • the embodiment may also include creating a histogram from the current values of the deltas.
  • the embodiment may further include, in response to creating the histogram, performing a scale-up of the allocated computational resources based on a percentage of data points that fall above the pre-defined max-latency threshold.
  • Figure 1 illustrates an exemplary networked computer environment according to at least one embodiment.
  • Figure 2 illustrates an operational flowchart for allocating computational resources in a speech-to-text auto-scaling process according to at least one embodiment.
  • Figure 3 is a functional block diagram of a software build quality assessment process according to at least one embodiment.
  • Figure 4 depicts a cloud computing environment according to an embodiment of the present invention.
  • Figure 5 depicts abstraction model layers according to an embodiment of the present invention.
  • Embodiments of the present invention relate to the field of computing, and more particularly to a speech-to-text auto-scaling system.
  • the following described exemplary embodiments provide a system, method, and program product to, among other things, utilize speech-to-text and natural language processing (NLP) to dynamically generate metrics that correlate with the user experience and the computational resources needed at any given time and, accordingly, allocate the computational resources necessary to keep latency within an acceptable range.
  • NLP natural language processing
  • computational resources and “backend servers” are used interchangeably herein. Therefore, the present embodiment has the capacity to improve the technical field of speech-to-text auto-scaling by allowing a natural and smooth interaction between the user and a cloud-based speech-to-text service.
  • speech-to-text relates to the field of transcribing words into textual form based on spoken language.
  • Real-time guarantees and in particular user-perceived latency are central to the user experience in all speech-to-text use cases that involve a live interaction between the user and the cloud-based speech-to-text service.
  • Real use cases may include, but are not limited to, closed-captioning, automated agents, and dictation.
  • recognition transcripts must be delivered by a speech recognition engine with little delay.
  • backend servers lacking headroom in terms of available computational resources to accommodate the dynamic central processing unit (CPU) requirements of the speech recognition engine.
  • computational resources may be allocated based on need and latency as well as cost are kept within the acceptable range.
  • a delta for each word in the recognition transcript may be computed.
  • the computed delta may be a time difference between a wall clock time when audio for the word is sent to the speech recognition engine, and the time when the word is delivered to a client, i.e., an application layer.
  • the deltas may be submitted to a group of metrics servers which are configured to collect the deltas.
  • a group of horizontal auto-scalers may periodically request from the metrics servers current values of the deltas. In at least one embodiment, if the current values of the deltas exceed a pre-defined maximum-latency (max-latency) threshold, the group of horizontal auto-scalers may trigger a scale-up operation and add more computational resources to the speech recognition engine running in the remote datacenter.
  • max-latency maximum-latency
  • the computational resources may be added incrementally until the current values of the deltas fall within the acceptable range for latency.
  • the group of horizontal auto-scalers may trigger a scale-down operation and reduce the computational resources allocated to the speech recognition engine running in the remote datacenter.
  • the computational resources may be reduced incrementally until the current values of the deltas fall within the acceptable range for latency.
  • the present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration
  • the computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention
  • the computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device.
  • the computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • a non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , a static random access memory (SRAM) , a portable compact disc read-only memory (CD-ROM) , a digital versatile disk (DVD) , a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or Flash memory erasable programmable read-only memory
  • SRAM static random access memory
  • CD-ROM compact disc read-only memory
  • DVD digital versatile disk
  • memory stick a floppy disk
  • a mechanically encoded device such as punch-cards or raised structures in a groove having instructions
  • a computer readable storage medium is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable) , or electrical signals transmitted through a wire.
  • Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network.
  • the network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
  • Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the "C" programming language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN) , or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider) .
  • electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA) , or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
  • These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
  • the computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function (s) .
  • the functions noted in the blocks may occur out of the order noted in the Figures.
  • two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • the following described exemplary embodiments provide a system, method, and program product to determine in real time whether the allocated computational resources are sufficient to keep latency within the acceptable range or whether the allocated computational resources require adjustment.
  • the networked computer environment 100 may include client computing device 102 and a server 112 interconnected via a communication network 114.
  • the networked computer environment 100 may include a plurality of client computing devices 102 and servers 112, of which only one of each is shown for illustrative brevity.
  • the communication network 114 may include various types of communication networks, such as a wide area network (WAN) , local area network (LAN) , a telecommunication network, a wireless network, a public switched network and/or a satellite network.
  • the communication network 114 may include connections, such as wire, wireless communication links, or fiber optic cables. It may be appreciated that Figure 1 provides only an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environments may be made based on design and implementation requirements.
  • Client computing device 102 may include a processor 104 and a data storage device 106 that is enabled to host and run a software program 108 and a speech-to-text auto-scaling program 110A and communicate with the server 112 via the communication network 114, in accordance with one embodiment of the invention.
  • Client computing device 102 may be, for example, a mobile device, a telephone, a personal digital assistant, a netbook, a laptop computer, a tablet computer, a desktop computer, or any type of computing device capable of running a program and accessing a network.
  • the client computing device 102 may include internal components 302a and external components 304a, respectively.
  • the server computer 112 may be a laptop computer, netbook computer, personal computer (PC) , a desktop computer, or any programmable electronic device or any network of programmable electronic devices capable of hosting and running a speech-to-text auto-scaling program 110B and a database 116 and communicating with the client computing device 102 via the communication network 114, in accordance with embodiments of the invention.
  • the server computer 112 may include internal components 302b and external components 304b, respectively.
  • the server 112 may also operate in a cloud computing service model, such as Software as a Service (SaaS) , Platform as a Service (PaaS) , or Infrastructure as a Service (IaaS) .
  • the server 112 may also be located in a cloud computing deployment model, such as a private cloud, community cloud, public cloud, or hybrid cloud.
  • the speech-to-text auto-scaling program 110A, 110B may be a program capable of computing a delta for each word in a transcript between a wall clock time and a time when the word is delivered to a client, i.e., an application layer, submitting the deltas to a group of metrics servers configured to collect the deltas, requesting from the metrics servers current values of the deltas, determining whether the current values of the deltas exceed a pre-defined threshold, and adjusting computational resource allocation based on a frequency of the current values of the deltas that exceed the pre-defined threshold.
  • the speech-to-text auto-scaling method is explained in further detail below with respect to Figure 2.
  • the speech-to-text auto scaling program 110A, 110B computes the delta for each word in the recognition transcript.
  • the computed deltas may be a time difference between the wall clock time when the audio for the word is sent to the speech recognition engine, and the time when the word is delivered to the client, i.e., the application layer.
  • the audio may be considered sent to the speech recognition engine the moment the word is spoken by the user.
  • the audio may be considered delivered to the client the moment the word is transcribed. For example, if a word is spoken and timestamped at 1: 00: 00 p.
  • the computed delta may be determined to be 12 seconds.
  • the computed deltas may be an end-to-end latency measurement that expresses quality of service in terms of latency as experienced by the user for a particular audio session.
  • a histogram may be created from the current values of the deltas.
  • the scale-up or scale-down of the computational resources may be based on a percentage of data points that fall above the pre-defined max-latency threshold. For example, if 5%of the computed deltas are above X seconds, the speech-to-text auto-scaling program 110A, 110B may scale-up the number of backend servers by Y percent.
  • the pre-defined max-latency threshold and the pre-defined min-latency threshold may be changed in accordance with user cases having different sensitivities to latency. For example, in an audio session where there is cross-talk and background noise, the pre-defined max-latency threshold may be lowered in order do devote more computational resources to that particular session.
  • the speech-to-text auto-scaling program 110A, 110B submits the current values of the deltas to the group of metrics servers which are configured to collect the deltas.
  • the current values of the deltas may be submitted via inter-process communication, in which the speech-to-text auto-scaling program 110A, 110B sends a request, and the group of metrics servers respond to the request.
  • the speech-to-text auto-scaling program 110A, 110B may send the current values of the deltas to the metrics servers, and the metrics servers may accept the submission of these current values.
  • the speech-to-text auto-scaling program 110A, 110B causes the group of horizontal auto-scalers to periodically request from the metrics servers the current values of the deltas.
  • the request may be made every 10 seconds.
  • the timing of the periodic request may be changed.
  • the group of horizontal auto-scalers may make the request every 8 seconds or every 12 seconds.
  • the group of horizontal auto-scalers may utilize a metrics application programming interface (API) in order to obtain the current values of the deltas from the metrics servers.
  • the metrics API may be a software intermediary which sends a request and delivers a response analogous to the inter-process communication described above.
  • the group of horizontal auto-scalers may request from the metrics servers the current values of the deltas every 10 seconds, and the API may deliver the current values back to the group of horizontal auto-scalers.
  • the metrics servers may be configured to send the current values of the deltas to the group of horizontal auto-scalers without the request from the group of horizontal auto-scalers.
  • the group of metrics servers may utilize the metrics API described above to send the current values of the deltas to the group of horizontal auto-scalers.
  • the metrics servers may submit the current values of the deltas to the group of horizontal auto-scalers, and the group of horizontal auto-scalers may accept the submission of the current values of the deltas.
  • the speech-to-text auto-scaling program 110A, 110B determines whether the current values of the deltas exceed the pre-defined maximum-latency (max-latency) threshold. The determination may be made based on an analysis of how many deltas exceed the pre-defined max-latency threshold and how many deltas fall below the pre-defined minimum-latency (min-latency) threshold. If the speech-to-text auto-scaling program 110A, 110B determines that the current values of the deltas exceed the pre-defined max-latency threshold, then the speech-to-text auto-scaling process proceeds to step 210 to adjust computational resource allocation based on the frequency of the current values of the deltas that exceed the pre-defined max-latency threshold.
  • the speech-to-text auto-scaling program 110A, 110B determines whether the current values of the deltas fall below the pre-defined min-latency threshold. If the speech-to-text auto-scaling program 110A, 110B determines that the current values of the deltas fall below the pre-defined min-latency threshold, then the speech-to-text auto-scaling process proceeds to step 212 to adjust computational resource allocation based on the frequency of the current values of the deltas that fall below the pre-defined min-latency threshold.
  • the speech-to-text auto-scaling program 110A, 100B adjusts the allocation of computational resources based on the frequency of the current values of the deltas that exceed the pre-defined max-latency threshold. For example, if the pre-defined max-latency threshold is exceeded more than Y times during at least Z seconds, the group of horizontal auto-scalers may trigger the scale-up operation and add more computational resources to the speech recognition engine running in the remote datacenter. A default number of computational resources may be initially allocated to the speech recognition engine before the current values of the deltas are available. For example, at least one computational resource may be allocated to the speech recognition engine at the start of the audio session.
  • the group of horizontal auto-scalers may trigger the scale-up operation by sending a signal to monitoring circuitry inside the backend servers in order to boot up the backend servers.
  • the computational resources may be added incrementally until the current values of the deltas fall within the acceptable range for latency.
  • a maximum number of computational resources may be allocated to the speech recognition engine to prevent over-allocation of the computational resources to any one audio session.
  • the speech-to-text auto-scaling program 110A, 110B may be configured to throttle new audio session requests from the users in order to guarantee the quality of service of the already established audio sessions. For example, if 90%of the available computational resources are currently allocated to all of the audio sessions combined, then the speech-to-text auto-scaling program 110A, 110B may throttle new audio session requests.
  • the speech-to-text auto-scaling program 110A, 110B adjusts the allocation of computational resources based on the frequency of the current values of the deltas that fall below the pre-defined minimum-latency (min-latency) threshold. For example, if the pre-defined min-latency threshold is not exceeded more than Y times during at least Z seconds, the group of horizontal auto-scalers may trigger the scale-down operation and reduce the computational resources allocated to the speech recognition engine running in the remote datacenter. The group of horizontal auto-scalers may trigger the scale-down operation by sending a signal to the monitoring circuitry inside the backend servers in order to power down the backend servers. Likewise, the computational resources may be reduced incrementally until the current values of the deltas fall within the acceptable range for latency.
  • min-latency pre-defined minimum-latency
  • a minimum number of computational resources may be allocated to the speech recognition engine so as not to significantly affect the quality of service of the audio sessions. For example, at least 10%of available computational resources may be allocated to the speech recognition engine at any given time. Therefore, even if the current values of the deltas fall within the acceptable range for latency, a number of computational resources may be devoted to each audio session to guarantee the quality of service.
  • Figure 2 provides only an illustration of one implementation and does not imply any limitations with regard to how different embodiments may be implemented. Many modifications to the depicted environments may be made based on design and implementation requirements.
  • Figure 3 is a block diagram 300 of internal and external components of the client computing device 102 and the server 112 depicted in Figure 1 in accordance with an embodiment of the present invention. It should be appreciated that Figure 3 provides only an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environments may be made based on design and implementation requirements.
  • the data processing system 302, 304 is representative of any electronic device capable of executing machine-readable program instructions.
  • the data processing system 302, 304 may be representative of a smart phone, a computer system, PDA, or other electronic devices.
  • Examples of computing systems, environments, and/or configurations that may represented by the data processing system 302, 304 include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputer systems, and distributed cloud computing environments that include any of the above systems or devices.
  • the client computing device 102 and the server 112 may include respective sets of internal components 302 a, b and external components 304 a, b illustrated in Figure 3.
  • Each of the sets of internal components 302 include one or more processors 320, one or more computer-readable RAMs 322, and one or more computer-readable ROMs 324 on one or more buses 326, and one or more operating systems 328 and one or more computer-readable tangible storage devices 330.
  • each of the computer-readable tangible storage devices 330 is a magnetic disk storage device of an internal hard drive.
  • each of the computer-readable tangible storage devices 330 is a semiconductor storage device such as ROM 324, EPROM, flash memory or any other computer-readable tangible storage device that can store a computer program and digital information.
  • Each set of internal components 302 a, b also includes a R/W drive or interface 332 to read from and write to one or more portable computer-readable tangible storage devices 338 such as a CD-ROM, DVD, memory stick, magnetic tape, magnetic disk, optical disk or semiconductor storage device.
  • a software program such as the speech-to-text auto-scaling program 110A, 110B, can be stored on one or more of the respective portable computer-readable tangible storage devices 338, read via the respective R/W drive or interface 332, and loaded into the respective hard drive 330.
  • Each set of internal components 302 a, b also includes network adapters or interfaces 336 such as a TCP/IP adapter cards, wireless Wi-Fi interface cards, or 3G or 4G wireless interface cards or other wired or wireless communication links.
  • the software program 108 and the speech-to-text auto-scaling program 110A in the client computing device 102 and the speech-to-text auto-scaling program 110B in the server 112 can be downloaded to the client computing device 102 and the server 112 from an external computer via a network (for example, the Internet, a local area network or other, wide area network) and respective network adapters or interfaces 336.
  • a network for example, the Internet, a local area network or other, wide area network
  • the network may comprise copper wires, optical fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers.
  • Each of the sets of external components 304 a, b can include a computer display monitor 344, a keyboard 342, and a computer mouse 334. External components 304 a, b can also include touch screens, virtual keyboards, touch pads, pointing devices, and other human interface devices.
  • Each of the sets of internal components 302 a, b also includes device drivers 340 to interface to computer display monitor 344, keyboard 342, and computer mouse 334.
  • the device drivers 340, R/W drive or interface 332, and network adapter or interface 336 comprise hardware and software (stored in storage device 330 and/or ROM 324) .
  • Cloud computing is a model of service delivery for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g. networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with a provider of the service.
  • This cloud model may include at least five characteristics, at least three service models, and at least four deployment models.
  • On-demand self-service a cloud consumer can unilaterally provision computing capabilities, such as server time and network storage, as needed automatically without requiring human interaction with the service’s provider.
  • Resource pooling the provider’s computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically assigned and reassigned according to demand. There is a sense of location independence in that the consumer generally has no control or knowledge over the exact location of the provided resources but may be able to specify location at a higher level of abstraction (e.g., country, state, or datacenter) .
  • Rapid elasticity capabilities can be rapidly and elastically provisioned, in some cases automatically, to quickly scale out and rapidly released to quickly scale in. To the consumer, the capabilities available for provisioning often appear to be unlimited and can be purchased in any quantity at any time.
  • Measured service cloud systems automatically control and optimize resource use by leveraging a metering capability at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts) . Resource usage can be monitored, controlled, and reported providing transparency for both the provider and consumer of the utilized service.
  • level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts) .
  • SaaS Software as a Service: the capability provided to the consumer is to use the provider’s applications running on a cloud infrastructure.
  • the applications are accessible from various client devices through a thin client interface such as a web browser (e.g., web-based e-mail) .
  • a web browser e.g., web-based e-mail
  • the consumer does not manage or control the underlying cloud infrastructure including network, servers, operating systems, storage, or even individual application capabilities, with the possible exception of limited user-specific application configuration settings.
  • PaaS Platform as a Service
  • the consumer does not manage or control the underlying cloud infrastructure including networks, servers, operating systems, or storage, but has control over the deployed applications and possibly application hosting environment configurations.
  • IaaS Infrastructure as a Service
  • the consumer does not manage or control the underlying cloud infrastructure but has control over operating systems, storage, deployed applications, and possibly limited control of select networking components (e.g., host firewalls) .
  • Private cloud the cloud infrastructure is operated solely for an organization. It may be managed by the organization or a third party and may exist on-premises or off-premises.
  • Public cloud the cloud infrastructure is made available to the general public or a large industry group and is owned by an organization selling cloud services.
  • Hybrid cloud the cloud infrastructure is a composition of two or more clouds (private, community, or public) that remain unique entities but are bound together by standardized or proprietary technology that enables data and application portability (e.g., cloud bursting for load-balancing between clouds) .
  • a cloud computing environment is service oriented with a focus on statelessness, low coupling, modularity, and semantic interoperability.
  • An infrastructure comprising a network of interconnected nodes.
  • cloud computing environment 40 comprises one or more cloud computing nodes 100 with which local computing devices used by cloud consumers, such as, for example, personal digital assistant (PDA) or cellular telephone 44A, desktop computer 44B, laptop computer 44C, and/or automobile computer system 44N may communicate.
  • Nodes 100 may communicate with one another. They may be grouped (not shown) physically or virtually, in one or more networks, such as Private, Community, Public, or Hybrid clouds as described hereinabove, or a combination thereof.
  • This allows cloud computing environment 40 to offer infrastructure, platforms and/or software as services for which a cloud consumer does not need to maintain resources on a local computing device.
  • computing devices 44A-N shown in Figure 4 are intended to be illustrative only and that computing nodes 100 and cloud computing environment 40 can communicate with any type of computerized device over any type of network and/or network addressable connection (e.g., using a web browser) .
  • FIG. 5 a set of functional abstraction layers 500 provided by cloud computing environment 40 is shown. It should be understood in advance that the components, layers, and functions shown in Figure 5 are intended to be illustrative only and embodiments of the invention are not limited thereto. As depicted, the following layers and corresponding functions are provided:
  • Hardware and software layer 60 includes hardware and software components.
  • hardware components include: mainframes 61; RISC (Reduced Instruction Set Computer) architecture based servers 62; servers 63; blade servers 64; storage devices 65; and networks and networking components 66.
  • software components include network application server software 67 and database software 68.
  • Virtualization layer 70 provides an abstraction layer from which the following examples of virtual entities may be provided: virtual servers 71; virtual storage 72; virtual networks 73, including virtual private networks; virtual applications and operating systems 74; and virtual clients 75.
  • management layer 80 may provide the functions described below.
  • Resource provisioning 81 provides dynamic procurement of computing resources and other resources that are utilized to perform tasks within the cloud computing environment.
  • Metering and Pricing 82 provide cost tracking as resources are utilized within the cloud computing environment, and billing or invoicing for consumption of these resources. In one example, these resources may comprise application software licenses.
  • Security provides identity verification for cloud consumers and tasks, as well as protection for data and other resources.
  • User portal 83 provides access to the cloud computing environment for consumers and system administrators.
  • Service level management 84 provides cloud computing resource allocation and management such that required service levels are met.
  • Service Level Agreement (SLA) planning and fulfillment 85 provide pre-arrangement for, and procurement of, cloud computing resources for which a future requirement is anticipated in accordance with an SLA.
  • SLA Service Level Agreement
  • Workloads layer 90 provides examples of functionality for which the cloud computing environment may be utilized. Examples of workloads and functions which may be provided from this layer include: mapping and navigation 91; software development and lifecycle management 92; virtual classroom education delivery 93; data analytics processing 94; transaction processing 95; and speech-to-text auto-scaling through natural language description 96. Speech-to-text auto-scaling through natural language description 96 may relate to dynamically generating metrics that correlate with the user experience and computational resources needed at any given time and allocating the computational resources necessary to keep latency within the acceptable range.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Transfer Between Computers (AREA)
  • Machine Translation (AREA)
PCT/CN2021/116202 2020-09-03 2021-09-02 Speech-to-text auto-scaling for live use cases Ceased WO2022048595A1 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2023514502A JP7748783B2 (ja) 2020-09-03 2021-09-02 ライブ・ユース・ケースの為のスピーチ・トゥ・テキスト自動スケーリング
GB2304504.0A GB2614179A (en) 2020-09-03 2021-09-02 Speech-to-text auto-scaling for live use cases
DE112021003525.8T DE112021003525B4 (de) 2020-09-03 2021-09-02 Automatische sprache-zu-text-skalierung für live-anwendungsfälle
CN202180053854.4A CN116194987B (zh) 2020-09-03 2021-09-02 用于实况使用情况的语音到文本自动缩放

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/010,866 2020-09-03
US17/010,866 US11521617B2 (en) 2020-09-03 2020-09-03 Speech-to-text auto-scaling for live use cases

Publications (1)

Publication Number Publication Date
WO2022048595A1 true WO2022048595A1 (en) 2022-03-10

Family

ID=80358863

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/116202 Ceased WO2022048595A1 (en) 2020-09-03 2021-09-02 Speech-to-text auto-scaling for live use cases

Country Status (6)

Country Link
US (1) US11521617B2 (https=)
JP (1) JP7748783B2 (https=)
CN (1) CN116194987B (https=)
DE (1) DE112021003525B4 (https=)
GB (1) GB2614179A (https=)
WO (1) WO2022048595A1 (https=)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12008416B2 (en) 2021-06-29 2024-06-11 Capital One Services, Llc Systems and methods for choosing an appropriate scaling technique for allocating computational resources to distributed applications
US12468574B2 (en) * 2021-10-28 2025-11-11 Capital One Services, Llc Systems and methods for dynamically scaling remote resources
US12165646B2 (en) * 2022-04-29 2024-12-10 Zoom Video Communications, Inc. Delta models for providing privatized speech-to-text during virtual meetings
US20230409393A1 (en) * 2022-05-24 2023-12-21 Microsoft Technology Licensing, Llc Systems and methods for autoscaling in datacenters

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000026902A1 (en) * 1998-11-04 2000-05-11 Syvox Corporation Apparatus and method for improved memory and resource management in a single-user or multi-user speech recognition system
US9269355B1 (en) * 2013-03-14 2016-02-23 Amazon Technologies, Inc. Load balancing for automatic speech recognition
US9514747B1 (en) * 2013-08-28 2016-12-06 Amazon Technologies, Inc. Reducing speech recognition latency
US9646601B1 (en) * 2013-07-26 2017-05-09 Amazon Technologies, Inc. Reduced latency text-to-speech system

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6629075B1 (en) * 2000-06-09 2003-09-30 Speechworks International, Inc. Load-adjusted speech recogintion
US6728677B1 (en) * 2001-01-31 2004-04-27 Nuance Communications Method and system for dynamically improving performance of speech recognition or other speech processing systems
JP4536481B2 (ja) * 2004-10-25 2010-09-01 インターナショナル・ビジネス・マシーンズ・コーポレーション コンピュータシステム、修正作業を支援するための方法、及びプログラム
US7953603B2 (en) * 2005-12-21 2011-05-31 International Business Machines Corporation Load balancing based upon speech processing specific factors
US9002713B2 (en) * 2009-06-09 2015-04-07 At&T Intellectual Property I, L.P. System and method for speech personalization by need
WO2011149558A2 (en) 2010-05-28 2011-12-01 Abelow Daniel H Reality alternate
US9098338B2 (en) 2010-12-17 2015-08-04 Verizon Patent And Licensing Inc. Work flow command processing system
US9769085B2 (en) 2012-05-04 2017-09-19 Citrix Systems, Inc. Systems and methods for adaptive application provisioning
US9069606B2 (en) 2012-05-08 2015-06-30 Adobe Systems Incorporated Autonomous application-level auto-scaling in a cloud
WO2014116888A1 (en) 2013-01-25 2014-07-31 REMTCS Inc. Network security system, method, and apparatus
US9064495B1 (en) * 2013-05-07 2015-06-23 Amazon Technologies, Inc. Measurement of user perceived latency in a cloud based speech application
KR20150026405A (ko) * 2013-09-03 2015-03-11 삼성전자주식회사 음성 패킷 송수신 방법 및 이를 구현하는 전자 장치
WO2015105994A1 (en) 2014-01-08 2015-07-16 Callminer, Inc. Real-time conversational analytics facility
CN103942372B (zh) * 2014-04-04 2017-01-04 天津大学 基于fpga的有源配电网暂态实时仿真多速率接口方法
CN104182909A (zh) * 2014-08-21 2014-12-03 大连理工大学 一种水电系统优化调度的多核并行逐次逼近方法
US9535738B2 (en) 2015-04-03 2017-01-03 International Business Machines Corporation Migrating virtual machines based on relative priority of virtual machine in the context of a target hypervisor environment
US9848041B2 (en) 2015-05-01 2017-12-19 Amazon Technologies, Inc. Automatic scaling of resource instance groups within compute clusters
EP3494700A4 (en) * 2016-08-03 2020-01-15 Dejero Labs Inc. SYSTEM AND METHOD FOR CONTROLLING DATA CURRENT MODIFICATIONS
US10193822B1 (en) 2016-08-18 2019-01-29 Amazon Technologies, Inc. Predictive auto-scaling and reactive auto-scaling for network accessible messaging services
JP2019028538A (ja) 2017-07-26 2019-02-21 日本電信電話株式会社 オートスケール処理装置、オートスケール方法及びプログラム
CN109509465B (zh) * 2017-09-15 2023-07-25 阿里巴巴集团控股有限公司 语音信号的处理方法、组件、设备及介质
US11152005B2 (en) * 2019-09-11 2021-10-19 VIQ Solutions Inc. Parallel processing framework for voice to text digital media
US11183178B2 (en) * 2020-01-13 2021-11-23 Microsoft Technology Licensing, Llc Adaptive batching to reduce recognition latency

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000026902A1 (en) * 1998-11-04 2000-05-11 Syvox Corporation Apparatus and method for improved memory and resource management in a single-user or multi-user speech recognition system
US9269355B1 (en) * 2013-03-14 2016-02-23 Amazon Technologies, Inc. Load balancing for automatic speech recognition
US9646601B1 (en) * 2013-07-26 2017-05-09 Amazon Technologies, Inc. Reduced latency text-to-speech system
US9514747B1 (en) * 2013-08-28 2016-12-06 Amazon Technologies, Inc. Reducing speech recognition latency

Also Published As

Publication number Publication date
DE112021003525B4 (de) 2024-10-02
US20220068280A1 (en) 2022-03-03
GB202304504D0 (en) 2023-05-10
US11521617B2 (en) 2022-12-06
CN116194987B (zh) 2025-08-12
JP7748783B2 (ja) 2025-10-03
DE112021003525T5 (de) 2023-07-06
CN116194987A (zh) 2023-05-30
JP2023540495A (ja) 2023-09-25
GB2614179A (en) 2023-06-28

Similar Documents

Publication Publication Date Title
WO2022048595A1 (en) Speech-to-text auto-scaling for live use cases
US9998399B2 (en) Cloud independent tuning service for autonomously managed workloads
US10382264B2 (en) Fog computing for machine translation
US11900078B2 (en) Tuning a container orchestrator
US11334333B1 (en) Generation of adaptive configuration files to satisfy compliance
US10157607B2 (en) Real time speech output speed adjustment
US20200244745A1 (en) Gateway device allowing multiple infrastructural services to access multiple iot devices
US10025640B2 (en) Balancing work of tasks at a sending node of a transaction server
JP7705215B2 (ja) キュー内で待機する呼に関する最適化
US12444414B2 (en) Dynamic virtual assistant speech modulation
US11442629B2 (en) I/O performance in a storage system
US20220012525A1 (en) Histogram generation
US10657079B1 (en) Output processor for transaction processing system
US10680912B1 (en) Infrastructure resource provisioning using trace-based workload temporal analysis for high performance computing
US10158544B2 (en) Selecting communication channels based on categorizations and measurements
US11770411B2 (en) Prioritize endpoint selection based on criteria
US12235933B2 (en) Increasing trust formation and reduce oversight costs for autonomous agents
US12050937B2 (en) Preventing resource exploitation in mobile devices
US10574542B2 (en) System and method for distributing resources throughout a network
US20230056965A1 (en) Dynamic multi-stream deployment planner
US20220405042A1 (en) Audio management for a priority computing device application

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21863659

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023514502

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 202304504

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20210902

WWE Wipo information: entry into national phase

Ref document number: 2304504.0

Country of ref document: GB

WWP Wipo information: published in national office

Ref document number: 2304504.0

Country of ref document: GB

122 Ep: pct application non-entry in european phase

Ref document number: 21863659

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 202180053854.4

Country of ref document: CN