Search Results for author:
Found 21 papers, 6 papers with code
STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models
Albeit great performance of Transformer-based speech selfsupervised learning (SSL) models, their large parameter size and computational cost make them unfavorable to utilize.
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation
Transformer-based speech self-supervised learning (SSL) models, such as HuBERT, show surprising performance in various speech processing tasks.
AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination
Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters.
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning
Our method reduces the model to 23. 8% in size and 35. 9% in inference time compared to HuBERT.
Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck
Furthermore, we show that the proposed system improves performance in low-resource and cross-dataset settings of anti-spoofing task significantly, demonstrating that our system is also robust in terms of data size and data distribution.
Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings
Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words.
Meta-Learned Confidence for Transductive Few-shot Learning
A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples, or confidence-weighted average of all the query samples.
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech
Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge distillation.
A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments
At the same time, there is an increasing requirement for an SV system: it should be robust to short speech segments, especially in noisy and reverberant environments.
Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling
While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants.
Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classification
In this paper, we propose a multi-task learning (MTL) method to improve the performance of a MOS prediction model using the following two auxiliary tasks: spoofing detection (SD) and spoofing type classification (STC).
Pitchtron: Towards audiobook generation from ordinary people's voices
To deal with this issue, we propose two models, hard and soft pitchtron and release the toolkit and corpus that we have developed.
Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention
Keyword spotting (KWS) and speaker verification (SV) have been studied independently although it is known that acoustic and speaker domains are complementary.
Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a speaker feature extractor.
Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
By combining these two learning schemes, our model outperforms existing state-of-the-art speaker verification models learned with a standard supervised learning framework on short utterance (1-2 seconds) on the VoxCeleb datasets.
Dual Attention in Time and Frequency Domain for Voice Activity Detection
The results show that the focal loss can improve the performance in various imbalance situations compared to the cross entropy loss, a commonly used loss function in VAD.
Meta-Learned Confidence for Few-shot Learning
To tackle this issue, we propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries such that they improve the model's transductive inference performance on unseen tasks.
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings
Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection.
Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification
The first approach is soft VAD, which performs a soft selection of frame-level features extracted from a speaker feature extractor.
Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification
Furthermore, we apply deep length normalization by augmenting the loss function with ring loss.
Learning acoustic word embeddings with phonetically associated triplet network
Previous researches on acoustic word embeddings used in query-by-example spoken term detection have shown remarkable performance improvements when using a triplet network.
