Search Results for author:
Found 38 papers, 8 papers with code
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #4 on
Multi-task Language Understanding
on MMLU
PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding
Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Seq2seq for Automatic Paraphasia Detection in Aphasic Speech
In this paper, we propose a novel, sequence-to-sequence (seq2seq) model that is trained end-to-end (E2E) to perform both ASR and paraphasia detection tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
StemGen: A music generation model that listens
End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently.
A Foundation Model for Music Informatics
This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues.
Scaling Up Music Information Retrieval Training with Semi-Supervised Learning
To our knowledge, this is the first attempt to study the effects of scaling up both model and training data for a variety of MIR tasks.
Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic parse from speech have become more promising recently.
Text Generation with Speech Synthesis for ASR Data Augmentation
In this work, we explore text augmentation for ASR using large-scale pre-trained neural networks, and systematically compare those to traditional text augmentation methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Improving Fast-slow Encoder based Transducer with Streaming Deliberation
Experiments on Librispeech and in-house data show relative WER reductions (WERRs) from 3% to 5% with a slight increase in model size and negligible extra token emission latency compared with fast-slow encoder based transducer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities
Later, we use our optimal tokenization strategy to train multiple embedding and output model to further improve our result.
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers
We show how factoring the RNN-T's output distribution can significantly reduce the computation cost and power consumption for on-device ASR inference with no loss in accuracy.
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data.
Robust Singular Values based on L1-norm PCA
The L2-norm (sum of squared values) formulation of PCA promotes peripheral data points and, thus, makes PCA sensitive against outliers.
Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
Electrocardiogram (ECG) signal is one of the most effective sources of information mainly employed for the diagnosis and prediction of cardiovascular diseases (CVDs) connected with the abnormalities in heart rhythm.
Learning ASR pathways: A sparse multilingual ASR model
Neural network pruning compresses automatic speech recognition (ASR) models effectively.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
STOP: A dataset for Spoken Task Oriented Semantic Parsing
Furthermore, in addition to the human-recorded audio, we are releasing a TTS-generated version to benchmark the performance for low-resource domain adaptation of end-to-end SLU systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition
The two most popular loss functions for streaming end-to-end automatic speech recognition (ASR) are RNN-Transducer (RNN-T) and connectionist temporal classification (CTC).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Deliberation Model for On-Device Spoken Language Understanding
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Streaming parallel transducer beam search with fast-slow cascaded encoders
Streaming ASR with strict latency constraints is required in many speech recognition applications.
Neural-FST Class Language Model for End-to-End Speech Recognition
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework.
Scaling ASR Improves Zero and Few Shot Learning
With 4. 5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Measuring automatic speech recognition (ASR) system quality is critical for creating user-satisfying voice-driven applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
In order to achieve flexible and better accuracy and latency trade-offs, the following techniques are used.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
As speech-enabled devices such as smartphones and smart speakers become increasingly ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems that can run directly on-device; end-to-end (E2E) speech recognition models such as recurrent neural network transducers and their variants have recently emerged as prime candidates for this task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
DET gets similar accuracy as a baseline model with better latency on a large in-house data set by assigning a lightweight encoder for the beginning part of one utterance and a full-size encoder for the rest.
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area.
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding
We define SemDist as the distance between a reference and hypothesis pair in a sentence-level embedding space.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+14
Deep Shallow Fusion for RNN-T Personalization
End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the last few years due to their simplicity, compactness, and excellent performance on generic transcription tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Alignment Restricted Streaming Recurrent Neural Network Transducer
There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improving RNN Transducer Based ASR with Auxiliary Tasks
End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers.
Ranked #16 on
Speech Recognition
on LibriSpeech test-clean
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training.
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
For a low latency scenario with an average latency of 80 ms, Emformer achieves WER $3. 01\%$ on test-clean and $7. 09\%$ on test-other.
Classification of Huntington Disease using Acoustic and Lexical Features
Speech is a critical biomarker for Huntington Disease (HD), with changes in speech increasing in severity as the disease progresses.
Weak-Attention Suppression For Transformer Based Speech Recognition
Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
We explore options to use Transformer networks in neural transducer for end-to-end speech recognition.
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR
Grapheme-based acoustic modeling has recently been shown to outperform phoneme-based approaches in both hybrid and end-to-end automatic speech recognition (ASR), even on non-phonemic languages like English.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Transformer-based Acoustic Modeling for Hybrid Speech Recognition
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition.
Ranked #25 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
