Google Inc.

Asapp, Inc.

Prashant Sridhar

Ignacio Lopez Moreno

Quan Wang

Li Wan

Yang Yu

Hannah Muckenhirn

Kyu Jeong Han

Felix Wu

Kwangyoun Kim

Hannah Muckenhim

Techniques are disclosed that enable processing of audio data to generate one or more refined versions of audio data, where each of the refined versions of audio data isolate one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by processing a spectrogram representation of the audio data (generated by processing the audio data with a frequency transformation) using a mask generated by processing the spectrogram of the audio data and a speaker embedding for the single human speaker using a trained voice filter model. Output generated over the trained voice filter model is processed using an inverse of the frequency transformation to generate the refined audio data.

Targeted voice separation by speaker conditioned on spectrogram masking

The amount of future context used in a speech processing application allows for tradeoffs between performance and the delay in providing results to users. Existing speech processing applications may be trained with a specified future context size and perform poorly when used in production with a different future context size. A speech processing application trained using a stochastic future context allows a trained neural network to be used in production with different amounts of future context. During an update step in training, a future-context size may be sampled from a probability distribution, used to mask a neural network, and compute an output of the masked neural network. The output may then be used to compute a loss value and update parameters of the neural network. The trained neural network may then be used in production with different amounts of future context to provide greater flexibility for production speech processing applications.

Stochastic future context for speech processing

Methods and systems for training and/or using a language selection model for use in determining a particular language of a spoken utterance captured in audio data. Features of the audio data can be processed using the trained language selection model to generate a predicted probability for each of N different languages, and a particular language selected based on the generated probabilities. Speech recognition results for the particular language can be utilized responsive to selecting the particular language of the spoken utterance. Many implementations are directed to training the language selection model utilizing tuple losses in lieu of traditional cross-entropy losses. Training the language selection model utilizing the tuple losses can result in more efficient training and/or can result in a more accurate and/or robust model&#x2014;thereby mitigating erroneous language selections for spoken utterances.

Training and/or using a language selection model for automatically determining language for speech recognition of spoken utterance

Growing community of inventors

New York, NY, United States of America

Prashant Sridhar