431 citations · 524 across the 12 of their papers we have counts for
15 papers
Personalizing Keyword Spotting with Speaker Information
Beltrán Labrador, Pai Zhu, Guanlong Zhao +5
Keyword spotting systems often struggle to generalize to a diverse population with various accents and age groups. To address this challenge, we propose a novel approach that integ…
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
Andrew Hard, Kurt Partridge, Neng Chen +9
We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To comp…
Parameter-Free Attentive Scoring for Speaker Verification
Jason Pelecanos, Quan Wang, Yiling Huang +1
This paper presents a novel study of parameter-free attentive scoring for speaker verification. Parameter-free scoring provides the flexibility of comparing speaker representations…
Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
Quan Wang, Yang Yu, Jason Pelecanos +2
In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry informa…
Noisy student-teacher training for robust keyword spotting
Hyun-Jin Park, Pai Zhu, Ignacio Lopez Moreno +1
We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The propo…
SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System
Roza Chojnacka, Jason Pelecanos, Quan Wang +1
In this paper, we describe SpeakerStew - a hybrid system to perform speaker verification on 46 languages. Two core ideas were explored in this system: (1) Pooling training data of…
Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition
Jason Pelecanos, Quan Wang, Ignacio Lopez Moreno
Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-or…
VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition
Quan Wang, Ignacio Lopez Moreno, Mert Saglam +8
We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speec…
Version Control of Speaker Recognition Systems
Quan Wang, Ignacio Lopez Moreno
This paper discusses one of the most challenging practical engineering problems in speaker recognition systems - the version control of models and user profiles. A typical speaker…
Training Keyword Spotting Models on Non-IID Data with Federated Learning
Andrew Hard, Kurt Partridge, Cameron Nguyen +5
We demonstrate that a production-quality keyword-spotting model can be trained on-device using federated learning and achieve comparable false accept and false reject rates to a ce…
Personal VAD: Speaker-Conditioned Voice Activity Detection
Shaojin Ding, Quan Wang, Shuo-yiin Chang +2
In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming o…
Tuplemax Loss for Language Identification
Li Wan, Prashant Sridhar, Yang Yu +2
In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want…
VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Quan Wang, Hannah Muckenhirn, Kevin Wilson +7
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We ac…
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Ye Jia, Yu Zhang, Ron J. Weiss +8
We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen d…
Links: A High-Dimensional Online Clustering Method
Philip Andrew Mansfield, Quan Wang, Carlton Downey +2
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space. The algorithm is appropriate when it is nec…