Add to ORKGInternational audienceThe demand for content-based management and real-time manipulation of audio data is constantly increasing. This paper presents a method to identify temporal regions, in a segment of co-channel speech, as being either single-speaker or multi- speaker speech. The state of the art approach for this purpose is the kurtosis. In this paper, a set of complementary time- domain and frequency-domain features is studied. The employed classification scheme is the one-class SVM classifier. A recognition rate of 94.75 % is reached. The set of features providing the best performance is determined
In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture...
The acoustic-phonetic modeling component of most current speech recognition sys-tems calculates a sm...
Despite the recent progress of automatic speech recognition (ASR) driven by deep learning, conversat...
International audienceThe demand for content-based management and real-time manipulation of audio da...
An extension to the conventional speech / nonspeech classification framework is presented for a scen...
In this paper, a new cochannel speech separation algorithm us-ing multi-pitch extraction and speaker...
This paper discusses the performance of a classification algorithm that is capable of determining th...
This paper presents a novel Bayesian approach to the problem of co-channel speech. The problem is fo...
The analysis of scenarios in which a number of microphones record the activity of speakers, such as ...
Human listeners have the extraordinary ability to hear and recognize speech even when more than one ...
We propose new data selection approaches based on speaker discriminability features, including kurto...
Human listeners have the extraordinary ability to hear and recognize speech even when more than one ...
This thesis concerns the detection of overlapping speech segments and its further application for th...
This paper presents a new technique for segmenting an audio stream into pieces, each one contains sp...
Presented paper takes interest in a speaker identification problem. The attributes representing voic...
In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture...
The acoustic-phonetic modeling component of most current speech recognition sys-tems calculates a sm...
Despite the recent progress of automatic speech recognition (ASR) driven by deep learning, conversat...
International audienceThe demand for content-based management and real-time manipulation of audio da...
An extension to the conventional speech / nonspeech classification framework is presented for a scen...
In this paper, a new cochannel speech separation algorithm us-ing multi-pitch extraction and speaker...
This paper discusses the performance of a classification algorithm that is capable of determining th...
This paper presents a novel Bayesian approach to the problem of co-channel speech. The problem is fo...
The analysis of scenarios in which a number of microphones record the activity of speakers, such as ...
Human listeners have the extraordinary ability to hear and recognize speech even when more than one ...
We propose new data selection approaches based on speaker discriminability features, including kurto...
Human listeners have the extraordinary ability to hear and recognize speech even when more than one ...
This thesis concerns the detection of overlapping speech segments and its further application for th...
This paper presents a new technique for segmenting an audio stream into pieces, each one contains sp...
Presented paper takes interest in a speaker identification problem. The attributes representing voic...
In this paper, we consider speaker identificationfor the co-channel scenario in which speech mixture...
The acoustic-phonetic modeling component of most current speech recognition sys-tems calculates a sm...
Despite the recent progress of automatic speech recognition (ASR) driven by deep learning, conversat...