DocumentCode :
3113542
Title :
Multilingual speaker recognition on Indian languages
Author :
Sarkar, Santonu ; Rao, K. Sreenivasa ; Nandi, Dipanjan ; Kumar, S. B. Sunil
Author_Institution :
Sch. of Inf. Technol., Indian Inst. of Technol. Kharagpur, Kharagpur, India
fYear :
2013
fDate :
13-15 Dec. 2013
Firstpage :
1
Lastpage :
5
Abstract :
In this paper we explore the performance of multilingual speaker recognition systems developed on the IITKGP-MLILSC speech corpus. Closed-set speaker identification and speaker verification experiments are individually conducted on 13 widely spoken Indian languages. In particular, we focus on the effect of language mismatch in the speaker recognition performance of individual languages and all languages together. The standard GMM-based speaker recognition framework is used. While the average language-independent speaker identification rate is as high as 95.21%, an average equal error rate of 11.71% shows scope for further improvement in speaker verification performance.
Keywords :
Gaussian processes; speaker recognition; IITKGP-MLILSC speech corpus; Indian languages; average language-independent speaker identification; closed-set speaker identification; language mismatch; multilingual speaker recognition; speaker verification experiments; standard GMM-based speaker recognition framework; Equations; Mathematical model; Mel frequency cepstral coefficient; Speaker recognition; Speech; Vectors; Gaussian Mixture Models; Indian Languages; Multilingual Speaker Recognition; Speaker Verification;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
India Conference (INDICON), 2013 Annual IEEE
Conference_Location :
Mumbai
Print_ISBN :
978-1-4799-2274-1
Type :
conf
DOI :
10.1109/INDCON.2013.6726131
Filename :
6726131
Link To Document :
بازگشت