کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6960585 | 1452002 | 2017 | 16 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Monaural multi-talker speech recognition using factorial speech processing models
ترجمه فارسی عنوان
تشخیص گفتار چند سخنرانی تکاملی با استفاده از مدل پردازش گفتار فاکتوریل
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
مدل مارکف پنهان فاکتوریل، مجموعه ای از تیلور بردار، شناخت مخلوط گفتار تک مشترک رمزگشایی، دوبرابر ویتربی، شناسایی مشترک سخنرانان،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
چکیده انگلیسی
A Pascal challenge entitled monaural speech separation and recognition challenge was developed, targeting the problem of robust automatic speech recognition against speech-like noises which significantly degrade the performance of automatic speech recognition systems. In this challenge, two competing speakers say a simple command simultaneously and the objective is to recognize speech of the target speaker. Surprisingly, a team from IBM research could achieve performance better than human listeners on this task during the challenge. The IBM system consists of an intermediate speech separation and two single-talker speech recognition modules. This paper reconsiders the recognition task of this challenge based on gain adapted factorial speech processing models. It develops a joint-token passing algorithm for direct joint-decoding of target and masker speakers' mixed-signals, simultaneously. It uses maximum uncertainty during the joint-decoding, which cannot be used in the two-phased IBM system. This paper provides a detailed derivation of inference on these models based on the general inference procedures of probabilistic graphical models. Additionally, it uses deep neural networks for joint-speaker identification and their gain estimation, which makes these two steps easier than before while producing competitive results for these steps. The proposed method of this work outperforms past super-human results and even the results recently achieved using deep neural networks by Microsoft research. It achieved 5.3% absolute task performance improvement compared to the first super-human system and 2.5% absolute task performance improvement compared to its recent competitor.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Speech Communication - Brought to you by:Anil Neerukonda Institute of Technology and Sciences 'Renewal due by 31 Dec 2017'
Journal: Speech Communication - Brought to you by:Anil Neerukonda Institute of Technology and Sciences 'Renewal due by 31 Dec 2017'
نویسندگان
Mahdi Khademian, Mohammad Mehdi Homayounpour,