Search Results for author:
Found 15 papers, 3 papers with code
Multi-modal Adversarial Training for Zero-Shot Voice Cloning
The discriminator is used in a training pipeline that improves both the acoustic and prosodic features of a TTS model.
On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Our approach used a teacher-student framework to transfer knowledge from a larger, more complex model to a smaller, light-weight model using dual-view cross-correlation distillation and the teacher's codebook as learning objectives.
Small-footprint slimmable networks for keyword spotting
In this work, we present Slimmable Neural Networks applied to the problem of small-footprint keyword spotting.
Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data.
Fixed-point quantization aware training for on-device keyword-spotting
Furthermore, on an in-house KWS dataset, we show that our 8-bit FXP-QAT models have a 4-6% improvement in relative false discovery rate at fixed false reject rate compared to full precision FLP models.
Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
We organize our results in two embedded chipset settings: a) with commodity ARM NEON instruction set and 8-bit containers, we present accuracy, CPU, and memory results using sub 8-bit weights (4, 5, 8-bit) and 8-bit quantization of rest of the network; b) with off-the-shelf neural network accelerators, for a range of weight bit widths (1 and 5-bit), while presenting accuracy results, we project reduction in memory utilization.
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to learn a feature representation.
Transformer-Transducers for Code-Switched Speech Recognition
We live in a world where 60% of the population can speak two or more languages fluently.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language.
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
We propose a novel approach to semi-supervised automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition
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 and language recognition.
Neural Text Normalization with Subword Units
We find subword models with additional linguistic features yield the best performance (with a word error rate of 0. 17{\%}).
End-to-end Anchored Speech Recognition
The anchored segment refers to the wake-up word part of an audio stream, which contains valuable speaker information that can be used to suppress interfering speech and background noise.
Decoding Ipsilateral Finger Movements from ECoG Signals in Humans
For successful upper limb BCIs, it is important to decode finger movements from brain activity.
