Search Results for: language model customization

Results 21 - 30 of 63 Page 3 of 7
Results per-page: 10 | 20 | 50 | 100

Speech Analytics Course (technical training)

Relevance: 6%      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…

Gender Identification

Relevance: 6%      Posted on: 2018-04-16

Gender Identification is a language-, domain- and channel-independent technology that uses the acoustic characteristics of the recording to determine the gender of the speaker in question. This technology is able to distinguish between two genders: Male (M) and Female (F). Minimum of speech signal for identification: 9+ sec recommended Output scoring: likelihood ratio and percentage metric (0-100%) Typical use cases: filtering calls by gender, playing advertisement focused on specific gender, getting quick demographic analysis of the recordings. The speed of Gender Identification is up to 150 FtRT (depending on the model).

Terminology

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…

Age Estimation

Relevance: 6%      Posted on: 2018-04-12

Phonexia Age Estimation (AGE) estimates the age of a speaker from audio recording. The process of voiceprint extraction is similar to the extraction of SID, but as a result different features get extracted; therefore, the voiceprints extracted from AGE and SID are not mutually compatible. Technology Trained with emphasis on spontaneous telephony conversation The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies channel compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc. Input Input format for processing: WAV or RAW (8 or 16 bits linear coding), A-law or Mu-law, PCM, 8kHz+ sampling…

LM

Relevance: 6%      Posted on: 2018-02-01

Language Model (“vocabulary” in STT technology)

Keyword Spotting results explained

Relevance: 6%      Posted on: 2019-06-12

This article aims on giving more details about Keyword Spotting outputs and hints on how to tailor Keyword Spotting to suit best your needs. Scoring Keyword Spotting works by calculating likelihoods that at a given spot occurs a keyword or just any other speech, and comparing those two likelihoods. The following scheme shows Background model for anything before the keyword (1), the Keyword model (2) and a Background model of any speech parallel with the keyword model (3). Models 2 and 3 produce two likelihoods – Lkw and Lbg (any speech = background). Raw score is calculated as log likelihood…

LP

Relevance: 3%      Posted on: 2018-02-01

Language Print - output data from LID technology

Voice Activity Detection

Relevance: 3%      Posted on: 2018-04-02

Voice Activity Detection is a language-, domain- and channel-independent technology that identifies parts of audio recordings with speech content vs. non-speech content. It creates labels for speech and other signals in the recording; this can then serve as a decision point whether to process the recording by other technologies or not. VAD is usually part of rapid filtration process in deployment. Typical use cases are: detection of present or absent human speech for voice processing, filtering non-speech parts of the recording, filtering out recordings with not enough net speech to be processed by other technologies voice activated process, etc. The…

Speaker Diarization (DIAR)

Relevance: 3%      Posted on: 2017-06-26

About DIAR Phonexia Speaker Diarization (DIAR) enables segmentation of voices in one monochannel audio record. Technology Trained with emphasis on spontaneous telephony conversation The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies channel compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc. Input Input format for processing: WAV or RAW (8 or 16 bits linear coding), A-law or Mu-law, PCM, 8kHz+ sampling Output Log file with processed information (segmentation of speech, silence, and technical signals – ie. elimination of phone lines beeps, DTMF tones, music, pauses, etc.) Audio file extracted for each…