Search Results for author:
Found 29 papers, 7 papers with code
Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
Pre-training speech models on large volumes of data has achieved remarkable success.
Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
One of the difficulties of this competition is how to use unlabeled data.
Ranked #245 on
Image Classification
on ImageNet
(using extra training data)
Universal Phone Recognition with a Multilingual Allophone System
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages.
Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble
Grapheme-to-Phoneme (G2P) has many applications in NLP and speech fields.
Enabling Real-time Neural IME with Incremental Vocabulary Selection
Input method editor (IME) converts sequential alphabet key inputs to words in a target language.
Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining
While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data.
ASR2K: Speech Recognition for Around 2000 Languages without Audio
We achieve 50% CER and 74% WER on the Wilderness dataset with Crubadan statistics only and improve them to 45% CER and 69% WER when using 10000 raw text utterances.
Domain Robust Feature Extraction for Rapid Low Resource ASR Development
We demonstrate the effectiveness of using a pre-trained English recognizer, which is robust to such mismatched conditions, as a domain normalizing feature extractor on a low resource language.
Real-time Neural-based Input Method
The input method is an essential service on every mobile and desktop devices that provides text suggestions.
SHE2: Stochastic Hamiltonian Exploration and Exploitation for Derivative-Free Optimization
Derivative-free optimization (DFO) using trust region methods is frequently used for machine learning applications, such as (hyper-)parameter optimization without the derivatives of objective functions known.
Phoneme Level Language Models for Sequence Based Low Resource ASR
Building multilingual and crosslingual models help bring different languages together in a language universal space.
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
SANTLR: Speech Annotation Toolkit for Low Resource Languages
In this work, we present SANTLR: Speech Annotation Toolkit for Low Resource Languages.
Multilingual Speech Recognition with Corpus Relatedness Sampling
For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language.
Adversarial Music: Real World Audio Adversary Against Wake-word Detection System
In this work, we target our attack on the wake-word detection system, jamming the model with some inconspicuous background music to deactivate the VAs while our audio adversary is present.
Towards Zero-shot Learning for Automatic Phonemic Transcription
The difficulty of this task is that phoneme inventories often differ between the training languages and the target language, making it infeasible to recognize unseen phonemes.
AlloVera: A Multilingual Allophone Database
While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription.
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization
Despite recent advances in natural language processing and other language technology, the application of such technology to language documentation and conservation has been limited.
Revisiting Factorizing Aggregated Posterior in Learning Disentangled Representations
In this paper, we provide a theoretical explanation that low total correlation of sampled representation cannot guarantee low total correlation of the mean representation.
End-to-end Quantized Training via Log-Barrier Extensions
Quantization of neural network parameters and activations has emerged as a successful approach to reducing the model size and inference time on hardware that sup-ports native low-precision arithmetic.
Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages
With the aim of aiding development of spoken dialog systems in low resourced languages, we propose a novel acoustics based intent recognition system that uses discovered phonetic units for intent classification.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments
There is additionally interest in building language technologies for low-resource and endangered languages.
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Models pre-trained on multiple languages have shown significant promise for improving speech recognition, particularly for low-resource languages.
On Prosody Modeling for ASR+TTS based Voice Conversion
In voice conversion (VC), an approach showing promising results in the latest voice conversion challenge (VCC) 2020 is to first use an automatic speech recognition (ASR) model to transcribe the source speech into the underlying linguistic contents; these are then used as input by a text-to-speech (TTS) system to generate the converted speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
For example, when using MTL to model various user behaviors in RS, if we differentiate new users and new items from old ones, there will be a cartesian product style increase of tasks with multi-dimensional relations.
Zero-shot Learning for Speech Recognition with Universal Phonetic Model
Our model is able to recognize unseen phonemes in the target language, if only a small text corpus is available.
RTC-VAE: HARNESSING THE PECULIARITY OF TOTAL CORRELATION IN LEARNING DISENTANGLED REPRESENTATIONS
In the problem of unsupervised learning of disentangled representations, one of the promising methods is to penalize the total correlation of sampled latent vari-ables.
Phone Inventories and Recognition for Every Language
Identifying phone inventories is a crucial component in language documentation and the preservation of endangered languages.
Textless Direct Speech-to-Speech Translation with Discrete Speech Representation
Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years.
