Using MLP features in SRI's conversational speech recognition system
نویسندگان
چکیده
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) features. This paper focuses on the challenges arising when incorporating these nonstandard features into a full-scale speech-to-text (STT) system, as used by SRI in the Fall 2004 DARPA STT evaluations. First, we developed a series of time-saving techniques for training feature MLPs on 1800 hours of speech. Second, we investigated which components of a multipass, multi-front-end recognition system are most profitably augmented with MLP features for best overall performance. The final system obtained achieved a 2% absolute (10% relative) WER reduction over a comparable baseline system that did not include Tandem/HATs MLP features.
منابع مشابه
Incorporating Tandem/hats Mlp Features into Sri’s Conversational Speech Recognition System
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLPs). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) feat...
متن کاملUsing MLP Features in SRI’s Conversation
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) featu...
متن کاملConnectionist speaker normalization and adaptation
In a speaker-independent, large-vocabulary continuous speech recognition systems, recognition accuracy varies considerably from speaker to speaker, and performance may be significantly degraded for outlier speakers such as nonnative talkers. In this paper, we explore supervised speaker adaptation and normalization in the MLP component of a hybrid hidden Markov model/ multilayer perceptron versi...
متن کاملImproved Single System Conversational Telephone Speech Recognition with VGG Bottleneck Features
On small datasets, discriminatively trained bottleneck features from deep networks commonly outperform more traditional spectral or cepstral features. While these features are typically trained with small, fully-connected networks, recent studies have used more sophisticated networks with great success. We use the recent deep CNN (VGG) network for bottleneck feature extraction—previously used o...
متن کاملIncorporating tone-related MLP posteriors in the feature representation for Mandarin ASR
Tone has a crucial role in Mandarin speech in distinguishing ambiguous words. In most state-of-the-art Mandarin automatic speech recognition systems, tonal acoustic units are used and F0 features are appended to the spectral features (MFCC/PLP). However, a tone depends on the F0 contour of a time span much longer than a frame. Ideally, systems would compute the framelevel likelihood of a tone u...
متن کامل