Microsoft Technology Licensing, LLC

Huaming Wang

Zhuo Chen

Takuya Yoshioka

Xuedong D Huang

Yifan Gong

Zhenghao Wang

Sefik Emre Eskimez

Jinyu Li

Hosam Adel Khalil

Khuram Shahid

Kshitiz Kumar

Xiong Xiao

Xiaofei Wang

Min Tang

Veljko Miljanic

Hassan Taherian

Hemin Yang

Zirun Zhu

Teng Yi

Examples of array geometry agnostic multi-channel personalized speech enhancement (PSE) extract speaker embeddings, which represent acoustic characteristics of one or more target speakers, from target speaker enrollment data. Spatial features (e.g., inter-channel phase difference) are extracted from input audio captured by a microphone array. The input audio includes a mixture of speech data of the target speaker(s) and one or more interfering speaker(s). The input audio, the extracted speaker embeddings, and the extracted spatial features are provided to a trained geometry-agnostic PSE model. Output data is produced, which comprises estimated clean speech data of the target speaker(s) that has a reduction (or elimination) of speech data of the interfering speaker(s), without the trained PSE model requiring geometry information for the microphone array.

Array geometry agnostic multi-channel personalized speech enhancement

Systems and methods are provided for generating and operating a speech enhancement model optimized for generating noise-suppressed speech outputs for improved human listening and live captioning. A computing system obtains a speech enhancement model trained on a first training dataset to generate noise-suppressed speech outputs and an automatic speech recognition model trained on a second training dataset to generate transcription labels for spoken language utterances. A third training dataset comprising a set of spoken language utterances is applied to the speech enhancement model to obtain a first noise-suppressed speech output which is applied to the automatic speech recognition model to generate a noise-suppressed transcription output for the set of spoken language utterances. Speech enhancement model parameters are updated to optimize the speech enhancement model to generate optimized noise-suppressed speech outputs based on a comparison of the noise-suppressed transcription output and ground truth transcription labels.

Systems and methods for human listening and live captioning

Generally discussed herein are devices, systems, and methods for wake word verification. A method can include receiving, at a server, a message from a device indicating that an utterance of a user-defined wake word was detected at the device, the message including (a) audio samples or features extracted from the audio samples and (b) data indicating the user-defined wake word, retrieving or generating, at the server, a custom decoding graph for the user-defined wake word, wherein the decoding graph and the static portion of the wake word verification model form a custom wake word verification model for the user-defined wake word, executing the wake word verification model to determine a likelihood that the wake word was uttered, and providing a message to the device indicating whether wake was uttered based on the determined likelihood.

Online verification of custom wake word

Representative embodiments disclose mechanisms to separate and recognize multiple audio sources (e.g., picking out individual speakers) in an environment where they overlap and interfere with each other. The architecture uses a microphone array to spatially separate out the audio signals. The spatially filtered signals are then input into a plurality of separators, so each signal is input into a corresponding signal. The separators use neural networks to separate out audio sources. The separators typically produce multiple output signals for the single input signals. A post selection processor then assesses the separator outputs to pick the signals with the highest quality output. These signals can be used in a variety of systems such as speech recognition, meeting transcription and enhancement, hearing aids, music information retrieval, speech enhancement and so forth.

Multi-channel speech separation

Techniques and architectures may be used to generate and perform a process using weighted finite-state transducers involving generic input search graphs. The process need not pursue theoretical optimality and instead search graphs may be optimized without an a priori optimization step. The process may result in an automatic speech recognition (ASR) decoder that is substantially faster than ASR decoders the include the optimization step.

No loss-optimization for weighted transducer

Growing community of inventors

Clyde Hill, WA, United States of America

Huaming Wang