Systems and methods for a media guidance application that generates results in multiple languages for search queries. In particular, the media guidance application resolves multiple language barriers by taking automatic and manual user language settings and applying those settings to a variety of potential search results.

Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

A computer-implemented method for preparing training data for a speech recognition model is provided including obtaining a plurality of sentences from a corpus, dividing each phoneme in each sentence of the plurality of sentences into three hidden states, calculating, for each sentence of the plurality of sentences, a score based on a variation in duration of the three hidden states of each phoneme in the sentence, and sorting the plurality of sentences by using the calculated scores.

A computer-implemented method for preparing training data for a speech recognition model is provided including obtaining a plurality of sentences from a corpus, dividing each phoneme in each sentence of the plurality of sentences into three hidden states, calculating, for each sentence of the plurality of sentences, a score based on a variation in duration of the three hidden states of each phoneme in the sentence, and sorting the plurality of sentences by using the calculated scores.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for communication a shared artificial reality environment. Various aspects may include receiving an indication of artificial reality location information for a user. Aspects may also include determining an audio configuration for the user based on the artificial reality location information or an application. Aspects may also include determining a switch point for changing the audio configuration for audio between the user and the another user, such as based on the location of the another user. Aspects may also include changing the audio configuration to another audio configuration based on the switch point. Aspects may include outputting audio based on the another audio configuration.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for communication a shared artificial reality environment. Various aspects may include receiving an indication of artificial reality location information for a user. Aspects may also include determining an audio configuration for the user based on the artificial reality location information or an application. Aspects may also include determining a switch point for changing the audio configuration for audio between the user and the another user, such as based on the location of the another user. Aspects may also include changing the audio configuration to another audio configuration based on the switch point. Aspects may include outputting audio based on the another audio configuration.

A method of speech detection and speech enhancement in a speech detection and speech enhancement unit of Multipoint Conferencing Node (MCN) and a method of training the same. The method comprising receiving input audio segments, and determining an acoustic environment based on input audio auxiliary information, extracting T-F-domain features from the received input audio segments, determining if each of the received input audio segments is speech by inputting the T-F domain features into a speech detection classifier trained for the determined acoustic environment, determining, when one of the received input audio segments is speech, if the received audio segment is noisy speech by inputting the T-F domain features into a noise classifier using a statistical generative model representing the probability distributions of the T-F domain features of noisy speech trained for the determined acoustic environment, and applying a noise reduction mask on the received input audio segments according to the determination of the received audio segment is noisy speech

A method of speech detection and speech enhancement in a speech detection and speech enhancement unit of Multipoint Conferencing Node (MCN) and a method of training the same. The method comprising receiving input audio segments, and determining an acoustic environment based on input audio auxiliary information, extracting T-F-domain features from the received input audio segments, determining if each of the received input audio segments is speech by inputting the T-F domain features into a speech detection classifier trained for the determined acoustic environment, determining, when one of the received input audio segments is speech, if the received audio segment is noisy speech by inputting the T-F domain features into a noise classifier using a statistical generative model representing the probability distributions of the T-F domain features of noisy speech trained for the determined acoustic environment, and applying a noise reduction mask on the received input audio segments according to the determination of the received audio segment is noisy speech

A method includes receiving a first instance of raw audio data corresponding to a voice-based command and receiving a second instance of the raw audio data corresponding to an utterance of audible contents for an audio-based communication spoken by a user. When a voice filtering recognition routine determines to activate voice filtering for at least the voice of the user, the method also includes obtaining a respective speaker embedding of the user and processing, using the respective speaker embedding, the second instance of the raw audio data to generate enhanced audio data for the audio-based communication that isolates the utterance of the audible contents spoken by the user and excludes at least a portion of the one or more additional sounds that are not spoken by the user The method also includes executing.