Search Results for: STT performance

Results 1 - 20 of 42 Page 1 of 3
Results per-page: 10 | 20 | 50 | 100

SPE3 – Releases and Changelogs

Relevance: 100%      Posted on: 2020-09-12

Speech Engine (SPE) is developed as RESTfull API on top of Phonexia BSAPI. SPE was formerly known as BSAPI-rest (up to v2.x) or as Phonexia Server (up to v3.2.x). This page lists changes in SPE releases. Releases Changelogs Speech Engine 3.30.13 (09/11/2020) - DB v1401, BSAPI 3.30.13 Public release New: Updated STT and KWS model AR_XL to version 5.1.0 Speech Engine 3.32.0 (08/28/2020) - DB v1500, BSAPI 3.32.0 Non-public Feature Preview release New: Added support for Webhooks and WebSockets in stream processing New: Added support for preferred phrases in 5th generation of STT (see POST /technologies/stt or POST /technologies/stt/input_stream) New:…

Performance of the Speaker Identification 4th generation (SID4): Intel® Xeon® Platinum 8124M

Relevance: 65%      Posted on: 2019-10-30

Benchmark goals Find realistic performance using total recording length Find FTRT based exactly on net_speech (engineering sizing data) Find system performance using all physical cores Find system performance using all logical cores Infrastructure setup Intel® Xeon® Platinum 8124M is used in virtual machine with 8 physical cores reserved exclusively for this VM, Hyper Threading is enabled [16 logical cores available], 32GB RAM, 30GB SSD based storage, 1000 I/O.s-1  reserved per core Benchmark data setup Data set statistic: Number of files: 32 [300 seconds each] RAW recordings length ∑: 9600 [sec] Net speech length ∑: 4224.77 [sec] In the data set…

STT Language Model Customization tutorial

Relevance: 57%      Posted on: 2019-04-24

Language Model Customization tool (LMC) provides a way to improve the Speech To Text performance by creating customized language model. Language model is an important part of Phonexia Speech To Text. In a simplified way it can be imagined as a large dictionary with multiple statistics. The Speech To Text technology uses this dictionary and statistical model to convert audio signals into the proper text equivalents. Due to general diversity of spoken speech, the default generic language model may not acknowledge the importance of certain words over other words in certain situations. Language model customization is a way to inform the…

How to convert STT confusion network results to one-best

Relevance: 30%      Posted on: 2020-04-06

Confusion Network output is the most detailed Speech Engine STT output as it provides multiple word alternatives for individual timeslots of processed speech signal. Therefore many applications want use it as the main source of speech transcription and perform eventual conversion to less verbose output formats internally. This article provides the recommended way to do the conversion. Time slots and word alternatives: The recommended algorithm for converting Confusion Network (CN) to One-best is as follows: loop through all CN timeslots from start to end in each timeslot, get the input alternative with highest score and if it's not <null/> or…

How to configure STT realtime stream word detection parameters

Relevance: 27%      Posted on: 2020-03-28

One of the improvements implemented since Speech Engine 3.24 is neural-network based VAD, used for word- and segment detection. This article describes the segmenter configuration parameters and how they are affecting the realtime stream STT results. The default segmenter parametrs are as shown below: [vad.online_segmenter:SOnlineVoiceActivitySegmenterI] backward_extensions_length_ms=150 forward_extensions_length_ms=750 speech_threshold=0.5 Backward- and forward extension are intervals in miliseconds, which extend the part of the signal going to the decoder. Decoder is a component, which determines what a particular part of the signal contains (speech, silence, etc.). Based on that, decoder also decides whether segment has finished or not. Unlike in file processing…

Difference between on-the-fly and off-line type of transcription (STT)

Relevance: 26%      Posted on: 2017-12-11

Similarly as human, the ASR (STT) engine is doing the adaptation to an acoustic channel, environment and speaker. Also the ASR (STT) engine is learning more information about the content during time, that is used to improve recognition. The dictate engine, also known as on-the-fly transciption, does not look to the future and has information about just a few seconds of speech at the beginning of recordings. As the output is requested immediately during processing of the audio, recording engine can't predict what will come in next seconds of the speech. When access to the whole recording is granted during off-line transcription…


Relevance: 24%      Posted on: 2018-02-01

Phonexia Speech To Text, sometime also as Speech Transcription Technology (LVCSR based ASR technology)

Measuring of a software processing speed – what is the FtRT (Faster than Real Time)

Relevance: 15%      Posted on: 2019-10-30

Faster Than Real Time (FTRT) is metrics developed for defining software performance reference point. Using this metric you can collect "benchmark" data of real processing speed for reviewed software, which should be found - and reproduced - on exactly defined HW. Then, comparing various benchmarks result, you can compare performance of the specified software and its parts on different HW configurations. And vice versa - using the same metric you can compare software from different vendors on the same HW configuration and for the same processing task. We are recognizing two measurable metrics: Recording based FTRT is calculated from real…

Sizing of the computing units for speech technologies

Relevance: 8%      Posted on: 2018-02-02

Best practices for good sizing of Phonexia technologies depend on a few facts: Intense work with large data sets requires good performance and bandwidth between RAM and CPU. It all depends on the size of the files with technological models data, usually loaded into RAM and used intensively for computing operations Always think only about physical cores of CPU (HT, VT features can't help in performance) Also seek for CPUs with a large L3 cache. And the better CPUs are those with higher l3_cache_size/#_of_physical_CPU_cores ratio. We currently assume that CPUs from the current Intel Xeon Family in the 4th generation…

Browser3 – Releases and Changelogs

Relevance: 8%      Posted on: 2020-08-21

Phonexia Browser v3 (Browser3) is developed as client on top of Phonexia Speech Engine v3. Phonexia Browser is a successor of Phonexia Speech Intelligence Resolver v1 (SIR1). This page lists changes in Browser releases. Releases Changelogs Phonexia Browser v3.30.12, BSAPI 3.30.11 - Aug 20 2020 Public release Fixed: Transcription results intermittently displays words in wrong order Versions 3.30.9, 3.30.10 and 3.30.11 were skipped Phonexia Browser v3.31.3, BSAPI 3.30.11 - Aug 20 2020 Non-public Feature Preview release Fixed: Transcription results intermittently displays words in wrong order Phonexia Browser v3.31.2, BSAPI 3.31.0 - Jul 24 2020 Non-public Feature Preview release Fixed: STT

Speech Intelligence Resolver v1

Relevance: 7%      Posted on: 2017-05-18

About Phonexia Speech Intelligence Resolver v1 (SIR1) combines the power of speech technologies within a single application. The application automatically performs visualization of the record as well as filtering the speech metadata uncovered from your records effectively. Speech technologies implemented: Phonexia Speaker Identification (SID2) Phonexia Language Identification (LID2) Phonexia Gender identification (GID) Phonexia Voice Activity Detection (VAD) Phonexia Speaker Diarization (DIAR) Phonexia Keyword Spotting (KWS) Phonexia Speech Quality Estimator (SQE) Phonexia Speech Transcription (STT) SIR is a client application cooperating with REST servers. It can be used as a standalone application due to the integrated local REST server. It was…

How to configure Speech Engine workers

Relevance: 7%      Posted on: 2020-03-28

Worker is a working thread performing the actual files- or realtime streams processing in Speech Engine. This article helps to understand the Speech Engine workers and provides information how to configure workers for optimal performance and server utilization. The default workers configuration in settings/ is as shown below – 8 workers for files processing and 8 workers for realtime streams processing. These numbers mean the maximum number of simultaneously running tasks. # Multithread settings server.n_workers = 8 server.n_realtime_workers = 8 Requests for additional file processing tasks are put in a queue and processed according their order and priorities. Requests for…

Speech To Text results explained

Relevance: 6%      Posted on: 2019-05-27

This article aims on giving more details about Speech To Text outputs and hints on how to tailor Speech To Text to suit best your needs. In the process of transcribing speech, the Speech To Text technology usually identifies multiple alternatives for individual speech segments, as multiple phrases can have similar pronunciations, possibly with different word boundaries, e.g. “eight tea machines” vs. “eighty machines”. The technology provides various output types which show only single or multiple transcription alternatives. For processing realtime streams, two result modes are supported – one mode provides complete transcription, second mode provides incremental results. Output types…

What is a user configuration file and how to use it

Relevance: 6%      Posted on: 2020-03-28

Advanced users with appropriate knowledge (gained e.g. by taking the Phonexia Academy Advanced Training) may want to finetune behavior of the technologies to adapt to the nature of their audio data. Modifying original BSAPI configuration files directly can be dangerous – inappropriate changes may cause unpredicatble behavior and without having a backup of the unmodified file it's difficult to restore working state. User configuration files provide a way to override processing parameters without modifying original BSAPI configuration files. WARNING: Inappropriate configuration changes may cause serious issues! Make sure you really know what you are doing. User configuration file is a…


Relevance: 6%      Posted on: 2017-06-15

Document which briefly describes processes and relations in Phonexia Technologies with consideration on correct word usage.   SID - Speaker Identification Technology (about SID technology) which recognize the speaker in the audio based on the input data (usually database of voiceprints). XL3, L3,L2,S2 - Technology models of SID. Speaker enrollment - Process, where the speaker model is created (usually new record in the voiceprint database). Speaker model: 1/ should reach recommended minimums (net speech, audio quality), 2/ should be made with more net speech and thus be more robust. The test recordings (payload) are then compared to the model (see…

Voice Biometrics Course (technical training)

Relevance: 5%      Posted on: 2017-05-18

The Voice Biometrics course consist of the following modules. Please ask your Phonexia contact for detailed description. (YES = this part is mandatory for course)   VBS course Required time [h] Block name Block description YES 0,5 Intro & Phonexia Portfolio Intro & Phonexia Portfolio YES 0,5 Project focus - Explain basic needs Partner project related discussion focused mainly to finalizing training topics and agenda YES 0,75 Apps Designing and Developing - Licensing Gives trainee knowledge about type of licensing, and how to use the license file YES 0,75 Technologies - Data gathering and Quality measurement - basic Data gathering…

Speech Analytics Course (technical training)

Relevance: 5%      Posted on: 2017-05-18

The Speech Analytics course consists of the following modules. Please ask your Phonexia contact for detailed description. (YES = this part of the course is obligatory)   SAL course Required time [h] Block name Block description YES 0,5 Intro & Phonexia Portfolio Intro & Phonexia Portfolio YES 0,5 Project focus – Explain basic needs Discussion of partner project focused mainly on finalizing the training topics and agenda. YES 0,75 Application Design & Development – Licensing Presentation of types of licensing, and how to use the license file. YES 0,75 Technologies – Data gathering and Quality measurement – basic Description of…

SPE configuration

Relevance: 5%      Posted on: 2018-02-02

Basic explanation of configuration directives for SPE with hints & tips. Overview of for beginners.