Cisco's speaker segmentation and recognition system
نویسندگان
چکیده
This paper presents Cisco’s speaker segmentation and recognition (SSR) system, which is a part of a commercial product. Cisco SSR uses speaker segmentation and speaker recognition algorithms with a crowd sourcing approach to create speaker metadata. The speaker metadata makes the enterprise videos more accessible and more navigable by itself, and by its combination with other forms of metadata such as keywords. This paper illustrates various functional blocks of SSR and a typical user interface. The paper describes the specific implementations of speaker segmentation and recognition algorithms. The paper also describes the evaluation data and protocols plus results for both speaker segmentation and speaker recognition tasks. Speaker segmentation results show that Cisco SSR performs comparable to the state-of-the-art on RT-03F data. Speaker recognition results show that a small set of user provided labels can be effectively transferred to a continuously expanding set of videos.
منابع مشابه
Remes Speaker - Based Segmentation and Adaptation in Automatic Speech Recognition
With proper training, automatic speech recognition works quite well when tested in conditions similar to the training conditions, but with a new speaker or a new environment the system performance often degrades. Speaker-based adaptation alters the speech recognition system to better match a specific speaker and thus improves the speech recognition results. In order to use speaker adaptation, t...
متن کاملSpeaker segmentation and clustering in meetings
This paper describes the issue of automatic speaker segmentation and clustering for natural, multi-speaker meeting conversations. Two systems were developed and evaluated in the NIST RT-04S Meeting Recognition Evaluation, the Multiple Distant Microphone (MDM) system and the Individual Headset Microphone (IHM) system. The MDM system achieved a speaker diarization performance of 28.17%. This syst...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملIntra-session Variability Compensation for Speaker Segmentation
This paper addresses the problem of speaker segmentation in two speaker telephone conversations, proposing a segmentation approach based on factor analysis and a novel method for intra-session variability compensation to improve segmentation performance. The segmentation system is evaluated on the NIST Speaker Recognition Evaluation 2008 summed channel test condition, showing that intra-session...
متن کاملInfluence of Transition Cost in the Segmentation Stage of Speaker Diarization
In any speaker diarization system there is a segmentation phase and a clustering phase. Our system uses them in a single step in which segmentation and clustering are used iteratively until certain condition is met. In this paper we propose an improvement of the segmentation method that cancels a penalization that had been applied in previous works to any transition between speakers. We also st...
متن کامل