The Experts below are selected from a list of 90 Experts worldwide ranked by ideXlab platform
Frank K. Soong - One of the best experts on this subject based on the ideXlab platform.
-
State mapping for cross-Language Speaker adaptation in TTS
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
-
ICASSP - State mapping for cross-Language Speaker adaptation in TTS
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
Yi-ning Chen - One of the best experts on this subject based on the ideXlab platform.
-
State mapping for cross-Language Speaker adaptation in TTS
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
-
ICASSP - State mapping for cross-Language Speaker adaptation in TTS
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
Yao Qian - One of the best experts on this subject based on the ideXlab platform.
-
State mapping for cross-Language Speaker adaptation in TTS
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
-
ICASSP - State mapping for cross-Language Speaker adaptation in TTS
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
Yang Jiao - One of the best experts on this subject based on the ideXlab platform.
-
State mapping for cross-Language Speaker adaptation in TTS
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
-
ICASSP - State mapping for cross-Language Speaker adaptation in TTS
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Yi-ning Chen, Yao Qian, Yang Jiao, Frank K. SoongAbstract:Cross-Language Speaker adaptation has many interesting applications, e.g. speech-to-speech translation. However, in cross-Language Speaker adaptation, a common phoneme set, assumed to be used by different Speakers of the same Language, does not exist any longer. Instead, a nearest neighbor based phoneme mapping from one Language to the other has been adopted. In this study, we used our recently proposed sub-phonemic HMM state mapping for cross-Language adaptations. The sub-phonemic HMM states, due to their phonetic segment nature, tend to be more sharable across different Languages than phonemes. Kullback-Leibler divergence, an information-theoretic measure, is chosen here to measure the similarity between given states in different Languages. Experimental results show that new state mapping outperforms the phoneme mapping baseline system in terms of three objective measures: log spectral distance, F0 adaptation error and F0 correlations. In comparing with intra-Language adaptation, the cross-Language result of the new algorithm is also fairly decent.
Claude Alain - One of the best experts on this subject based on the ideXlab platform.
-
The Effects of Absolute Pitch and Tone Language on Pitch Processing and Encoding in Musicians
Music Perception, 2015Co-Authors: Stefanie Hutka, Claude AlainAbstract:Absolute pitch (AP) is the rare ability to identify or produce a specific pitch without a reference pitch, which appears to be more prevalent in tone-Language Speakers than non-tone-Language Speakers. Numerous studies support a close relationship between AP, music, and Language. Despite this relationship, the extent to which these factors contribute to the processing and encoding of pitch has not yet been investigated. Addressing this research question would provide insights into the relationship between music and Language, as well as the mechanisms of AP. To this aim, we recruited AP musicians and non-AP musicians who were either tone-Language (Mandarin and Cantonese) or non-tone Language Speakers. Participants completed a zero- and one-back working memory task using music and non-music (control) stimuli. In general, AP participants had better accuracy and faster reaction times than participants without AP. This effect remained even after controlling for the age at which participants began formal music lessons. We did not observe a performance advantage afforded by speaking a tone Language, nor a cumulative advantage afforded by having AP and being a tone-Language Speaker.
