The AT&amp;T WATSON Speech Recognizer

Goffin, Vincent; Allauzen, Cyril; Bocchieri, Enrico; Hakkani‐Tür, Dilek; Ljolje, Andrej; Parthasarathy, S.; Rahim, Mazin G.; Riccardi, Giuseppe; Saraçlar, Murat

doi:10.1109/icassp.2005.1415293

Cited by 47 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used AT&T Watson ASR [19] (with a trigram language model trained on HUB-4 training set) to produce 100-best hypotheses for each of the test audio files of the HUB-4 task. The 1-best and the 100-best oracle word accuracies are 63.7% and 66.6% respectively.…”

Section: Speech Recognition (Hub-4)mentioning

confidence: 99%

Feature-rich continuous language models for speech recognition

Mirowski

Chopra

Balakrishnan

et al. 2010

2010 IEEE Spoken Language Technology Workshop

View full text Add to dashboard Cite

State-of-the-art probabilistic models of text such as n-grams require an exponential number of examples as the size of the context grows, a problem that is due to the discrete word representation. We propose to solve this problem by learning a continuous-valued and lowdimensional mapping of words, and base our predictions for the probabilities of the target word on non-linear dynamics of the latent space representation of the words in context window. We build on neural networks-based language models; by expressing them as energy-based models, we can further enrich the models with additional inputs such as part-of-speech tags, topic information and graphs of word similarity. We demonstrate a significantly lower perplexity on different text corpora, as well as improved word accuracy rate on speech recognition tasks, as compared to Kneser-Ney backoff n-gram-based language models.

show abstract

Section: Speech Recognition (Hub-4)mentioning

confidence: 99%

Feature-rich continuous language models for speech recognition

Mirowski

Chopra

Balakrishnan

et al. 2010

2010 IEEE Spoken Language Technology Workshop

View full text Add to dashboard Cite

show abstract

“…From the bilanguage corpus B, we train an n-gram language model using standard tools (Goffin et al, 2005). The resulting language model is represented as a weighted finite-state automaton (S × T → [0, 1]).…”

Section: Sfst Modelmentioning

confidence: 99%

Statistical Machine Translation through Global Lexical Selection and Sentence Reconstruction

Bangalore¹,

Haffner²,

Kanthak³

2008

Learning Machine Translation

View full text Add to dashboard Cite

Machine translation of a source language sentence involves selecting appropriate target language words and ordering the selected words to form a well-formed target language sentence. Most of the previous work on statistical machine translation relies on (local) associations of target words/phrases with source words/phrases for lexical selection. In contrast, in this paper, we present a novel approach to lexical selection where the target words are associated with the entire source sentence (global) without the need to compute local associations. Further, we present a technique for reconstructing the target language sentence from the selected words. We compare the results of this approach against those obtained from a finite-state based statistical machine translation system which relies on local lexical associations.

show abstract

“…The AT&T Watson [10] speech recognizer was used to automatically convert each spoken review summary to text. Due to the scarcity of speech data available for the restaurant review domain, we had to rely on text sources to create a language model appropriate for this task.…”

Section: Speech Recognition For Spoken Reviewsmentioning

confidence: 99%

Can prosody inform sentiment analysis? Experiments on short spoken reviews

Mairesse

Polifroni

Fabbrizio

2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

While most online content is created using textual interfaces, recent improvements in speech recognition accuracy allows the creation of content through speech. This technology allows users to share reviews about entities of interest without any delay, using mobile devices. This paper builds on the previous work on textual sentiment analysis to investigate whether information in the speech signal can be used to predict sentiment from short spoken reviews. For this purpose we collected a short spoken reviews from 84 speakers. Results show that models trained on features characterizing the review's pitch significantly outperform a majority class baseline, without textual information. When taking text-based sentiment predictions into account, our results suggest that prosody can alleviate the effect of speech recognition errors on sentiment detection, however a larger dataset is needed to test whether this can be done without harming performance on low word error rates.

show abstract

The AT&T WATSON Speech Recognizer

Cited by 47 publications

References 9 publications

Feature-rich continuous language models for speech recognition

Feature-rich continuous language models for speech recognition

Statistical Machine Translation through Global Lexical Selection and Sentence Reconstruction

Can prosody inform sentiment analysis? Experiments on short spoken reviews

Contact Info

Product

Resources

About