Amazon Technologies, Inc.

Anil Kumar Nelakanti

Mayank Sharma

Prabhakar Gupta

Saravanan Santhamoorthy Theckyam

Honey Gupta

Palanivelu Balakrishnan

Kumar Keshav

Methods and apparatus are described for evaluating dubbing of media content. Phonemes in dubbed audio are extracted and mapped to visemes. Lip poses in video frames of the media content corresponding to the phonemes of the dubbed audio are compared to the visemes determined from the dubbed audio. A notification may be generated based on the comparison that indicates synchronization of the dubbed audio to lip poses of the video.

Audio-lip movement correlation measurement for dubbed content

Methods and apparatus are described for evaluating dubbing of media content. Emotions are identified based on combinations of attributes determined for segments of a source language audio and a dubbed audio. The emotions may be compared to determine emotional prosody transfer between the source audio and dubbed audio. Based on the comparison, a notification is generated indicating whether an emotion classification associated with the source audio matches an emotion classification associated with the dubbed audio.

Multi-task and multi-lingual emotion mismatch detection for automated dubbing

Described herein is a computer-implemented method for extracting and identifying an audio song. An audio file can be accessed by a computing device. A set of audio categories and a set of probabilities associated with the set of audio categories can be determined for a first audio clip. A subset of the set of audio categories can be determined based on a subset of the set of probabilities. Each audio category of the subset of the set of audio categories can correspond to an audio class label. Whether the first audio clip is part of a song can be determined. The song can be defined by combining the first audio clip with other audio clips.

Song generation using a pre-trained audio neural network

Techniques and apparatus for selecting audio content for a content entity in audio-visual content are described. An example technique involves identifying at least one content entity associated with a content item that is accessible to one or more users in a first language over a communication network. One or more attributes of the at least one content entity are determined. A plurality of audio content samples in a second language are obtained. Each audio content sample includes a different audio sample of a portion of speech of the content entity in the second language. A first audio content sample that satisfies a predetermined condition is determined, based on the plurality of audio content samples and the one or more attributes of the at least one content entity. An indication of the first audio content sample is provided.

Voice content selection for video content

Technologies are provided for automated quality assessment of translations. In some embodiments, quality of a translation can be assessed by generating a machine-learning (ML) model that classifies the translation as pertaining to one of three quality categories. A first quality category can include, for example, translations that are deemed satisfactory. A second quality category can include, for example, translations that are deemed subject to edition prior to being deemed satisfactory. A third quality category can include, for example, translations that are deemed unsatisfactory. The generated ML model can then be applied to the translation and a corresponding sentence in a source language in order to classify the translation as pertaining to one of the three categories.

Growing community of inventors

Bengaluru, India

Anil Kumar Nelakanti