Acoustic-to-Word Recognition with Sequence-to-Sequence Models

07/23/2018
by   Shruti Palaskar, et al.
0

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0% in Word Error Rate on the Switchboard corpus compared to prior work. In addition to these promising results, word-based models are more interpretable than character models, which have to be composed into words using a separate decoding step. We analyze the encoder hidden states and the attention behavior, and show that location-aware attention naturally represents words as a single speech-word-vector, despite spanning multiple frames in the input. We finally show that the Acoustic-to-Word model also learns to segment speech into words with a mean standard deviation of 3 frames as compared with human annotated forced-alignments for the Switchboard corpus.

READ FULL TEXT
research
04/09/2019

Who Needs Words? Lexicon-Free Speech Recognition

Lexicon-free speech recognition naturally deals with the problem of out-...
research
08/15/2017

Comparison of Decoding Strategies for CTC Acoustic Models

Connectionist Temporal Classification has recently attracted a lot of in...
research
12/08/2017

Building competitive direct acoustics-to-word models for English conversational speech recognition

Direct acoustics-to-word (A2W) models in the end-to-end paradigm have re...
research
08/18/2015

End-to-End Attention-based Large Vocabulary Speech Recognition

Many of the current state-of-the-art Large Vocabulary Continuous Speech ...
research
11/28/2017

Acoustic-To-Word Model Without OOV

Recently, the acoustic-to-word model based on the Connectionist Temporal...
research
02/05/2019

Model Unit Exploration for Sequence-to-Sequence Speech Recognition

We evaluate attention-based encoder-decoder models along two dimensions:...
research
09/21/2021

On the Difficulty of Segmenting Words with Attention

Word segmentation, the problem of finding word boundaries in speech, is ...

Please sign up or login with your details

Forgot password? Click here to reset