Arun Narayanan

BONE CONDUCTED SIGNAL GUIDED SPEECH ENHANCEMENT FOR VOICE ASSISTANT ON EARBUDS

Streaming Automatic Speech Recognition Via Differentially Private Fusion of Data From Multiple Sources

Computational Latencies Of End-To-End Models By Large Reduction Of The Number Of Encoder Output Frames

OPTIMIZING PERSONAL VAD FOR ON-DEVICE SPEECH RECOGNITION

Quantifying Unintended Memorization in Automated Speech Recognition Encoders

Streaming, Array-Agnostic, Full- and Sub-Band Modeling Front- End for Robust Automatic Speech Recognition

Using Synthetic Data to Improve Word Error Rate of Differentially Private ASR Models

PER-CORE GRADIENT CLIPPING IN MULTI-CORE TRAINING OF MACHINE LEARNING (ML) MODEL(S)

Acoustic Echo Cancellation For Digital Assistants Using Neural Echo Suppression and Multi-Microphone Noise Reduction

Acoustic Echo Cancellation With Text-To-Speech (TTS) Data Loopback

Joint Acoustic Echo Cancelation, Speech Enhancement, and Voice Separation for Automatic Speech Recognition

Transducer-Based Streaming Deliberation for Cascaded Encoders

TWO-PASS END TO END SPEECH RECOGNITION

EFFICIENT STREAMING NON-RECURRENT ON-DEVICE END-TO-END MODEL

Automated calling system

Automated calling system

Efficient streaming non-recurrent on-device end-to-end model

STFT-based echo muter

Automated calling system

Context aware beamforming of audio data

Efficient streaming non-recurrent on-device end-to-end model

Two-pass end to end speech recognition

Automated calling system