Add to ORKGWe propose a hybrid approach to foreign accent recognition combining both phonotactic and spectral based systems by treating the problem as a spoken language recognition task. We extract speech attribute features that represent speech and acoustic cues reflecting foreign accents of a speaker to obtain feature streams that are modeled with the i-vector method-ology. Testing on the Finnish Language Proficiency exam corpus, we find our proposed technique to achieve a signif-icant performance improvement over the state-of-the-art sys-tems using only spectral based features. Index Terms — Speech attributes, i-vector, foreign accent recognition, language recognitio
National audienceIn this paper we propose an automatic approach to foreign accent identification. Kn...
Traditionally, work in automatic accent recognition has followed a similar research trajectory to th...
We have recently proposed a universal acoustic characterisa-tion to foreign accent recognition, in w...
We propose a hybrid approach to foreign accent recognition combining both phonotactic and spectral b...
Abstract—We propose a unified approach to automatic foreign accent recognition. It takes advantage o...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
Recognition of foreign accented speech remains among the most difficult tasks in automatic speech re...
International audienceIn this paper we propose an automatic approach for foreign accent identificati...
The performance of voice-controlled systems is usually influenced by accented speech. To make these ...
Speaker accent is an important issue in the formulation of robust speaker independent recognition sy...
There have been significant improvements in automatic voice recognition technology. However, existin...
Advances in speech technology, speech signal processing and phonetic representation are leading to n...
The performance of speech recognition systems degrades when speaker accent is different from that in...
National audienceIn this paper we propose an automatic approach to foreign accent identification. Kn...
Traditionally, work in automatic accent recognition has followed a similar research trajectory to th...
We have recently proposed a universal acoustic characterisa-tion to foreign accent recognition, in w...
We propose a hybrid approach to foreign accent recognition combining both phonotactic and spectral b...
Abstract—We propose a unified approach to automatic foreign accent recognition. It takes advantage o...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
I-vector based recognition is a well-established technique in state-of-the-art speaker and language ...
Recognition of foreign accented speech remains among the most difficult tasks in automatic speech re...
International audienceIn this paper we propose an automatic approach for foreign accent identificati...
The performance of voice-controlled systems is usually influenced by accented speech. To make these ...
Speaker accent is an important issue in the formulation of robust speaker independent recognition sy...
There have been significant improvements in automatic voice recognition technology. However, existin...
Advances in speech technology, speech signal processing and phonetic representation are leading to n...
The performance of speech recognition systems degrades when speaker accent is different from that in...
National audienceIn this paper we propose an automatic approach to foreign accent identification. Kn...
Traditionally, work in automatic accent recognition has followed a similar research trajectory to th...
We have recently proposed a universal acoustic characterisa-tion to foreign accent recognition, in w...