151 citations · 251 across the 10 of their papers we have counts for
11 papers
On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Gene-Ping Yang, Yue Gu, Qingming Tang +2
Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in…
Small-footprint slimmable networks for keyword spotting
Zuhaib Akhtar, Mohammad Omar Khursheed, Dongsu Du +1
In this work, we present Slimmable Neural Networks applied to the problem of small-footprint keyword spotting. We show that slimmable neural networks allow us to create super-nets…
Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Chenyang Gao, Yue Gu, Francesco Caliva +1
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large m…
Fixed-point quantization aware training for on-device keyword-spotting
Sashank Macha, Om Oza, Alex Escott +5
Fixed-point (FXP) inference has proven suitable for embedded devices with limited computational resources, and yet model training is continually performed in floating-point (FLP).…
Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu +4
We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the…
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
Shaoshi Ling, Yuzong Liu
Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount o…
Transformer-Transducers for Code-Switched Speech Recognition
Siddharth Dalmia, Yuzong Liu, Srikanth Ronanki +1
We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation…
Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Chander Chandak, Zeynab Raeesy, Ariya Rastrow +5
This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for vo…
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
Shaoshi Ling, Yuzong Liu, Julian Salazar +1
We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we rec…
BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition
Shaoshi Ling, Julian Salazar, Yuzong Liu +1
We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker an…
End-to-end Anchored Speech Recognition
Yiming Wang, Xing Fan, I-Fan Chen +3
Voice-controlled house-hold devices, like Amazon Echo or Google Home, face the problem of performing speech recognition of device-directed speech in the presence of interfering bac…