Search Results for author:
Found 58 papers, 7 papers with code
Text Injection for Neural Contextual Biasing
Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping
Gradient clipping plays a vital role in training large-scale automatic speech recognition (ASR) models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data.
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
In the present work, we study one such strategy: applying multiple frame reduction layers in the encoder to compress encoder outputs into a small number of output frames.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers
ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours).
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
We conducted extensive experiments with a 2-billion parameter USM on a large-scale voice search dataset to evaluate our proposed method.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning
Automatic speech recognition (ASR) models are typically trained on large datasets of transcribed speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Massive End-to-end Models for Short Search Queries
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B model parameters.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Improving Joint Speech-Text Representations Without Alignment
The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly.
How to Estimate Model Transferability of Pre-Trained Speech Models?
In this work, we introduce a "score-based assessment" framework for estimating the transferability of pre-trained speech models (PSMs) for fine-tuning target tasks.
A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale
Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus.
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
Overall, they present a modular, powerful and cheap alternative to the standard encoder output, as well as the N-best hypotheses.
Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Such a model allows us to achieve always-on ambient speech recognition on edge devices with low-memory neural processors.
End-to-End Speech Recognition: A Survey
In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
We propose JEIT, a joint end-to-end (E2E) model and internal language model (ILM) training method to inject large-scale unpaired text into ILM during E2E training which improves rare-word speech recognition.
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition
In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dual Learning for Large Vocabulary On-Device ASR
Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once.
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
We explore unifying a neural segmenter with two-pass cascaded encoder ASR into a single model.
Modular Hybrid Autoregressive Transducer
In this work, we propose a modular hybrid autoregressive transducer (MHAT) that has structurally separated label and blank decoders to predict label and blank distributions, respectively, along with a shared acoustic encoder.
JOIST: A Joint Speech and Text Streaming Model For ASR
In addition, we explore JOIST using a streaming E2E model with an order of magnitude more data, which are also novelties compared to previous works.
Improving Deliberation by Text-Only and Semi-Supervised Training
Text-only and semi-supervised training based on audio-only data has gained popularity recently due to the wide availability of unlabeled text and speech data.
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition.
Improving Rare Word Recognition with LM-aware MWER Training
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the rescoring setups.
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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.
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
Our experiments show that for both losses, the WER on long-form speech reduces substantially as the training utterance length increases.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer And Large Scale Synthetic Data
We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.
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.
Learning Word-Level Confidence For Subword End-to-End ASR
We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging
End-to-end models that condition the output label sequence on all previously predicted labels have emerged as popular alternatives to conventional systems for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Cascaded encoders for unifying streaming and non-streaming ASR
The proposed model consists of streaming and non-streaming encoders.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction
We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
On a long-form YouTube test set, when the nonstreaming RNN-T model is trained with shorter segments of data, the proposed combination improves word error rate (WER) from 22. 3% to 14. 8%; when the streaming RNN-T model trained on short Search queries, the proposed techniques improve WER on the YouTube set from 67. 0% to 25. 3%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.
Deliberation Model Based Two-Pass End-to-End Speech Recognition
End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A comparison of end-to-end models for long-form speech recognition
In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Recognizing long-form speech using streaming end-to-end models
In this work, we examine the ability of E2E models to generalize to unseen domains, where we find that models trained on short utterances fail to generalize to long-form speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Two-Pass End-to-End Speech Recognition
However, this model still lags behind a large state-of-the-art conventional model in quality [2].
Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
Contextual automatic speech recognition, i. e., biasing recognition towards a given context (e. g. user's playlists, or contacts), is challenging in end-to-end (E2E) models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models.
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
We also investigate model complementarity: we find that we can improve WERs by up to 9% relative by rescoring N-best lists generated from a strong word-piece based baseline with either the phoneme or the grapheme model.
Ranked #49 on
Speech Recognition
on LibriSpeech test-clean
Streaming End-to-end Speech Recognition For Mobile Devices
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition.
From Audio to Semantics: Approaches to end-to-end spoken language understanding
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text (or top N hypotheses) into a set of domains, intents, and arguments.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Deep context: end-to-end contextual speech recognition
Our approach, which we re- fer to as Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR components along with embeddings of the context n-grams.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer
The model consists of an `encoder', which is initialized from a connectionist temporal classification-based (CTC) acoustic model, and a `decoder' which is partially initialized from a recurrent neural network language model trained on text data alone.
An analysis of incorporating an external language model into a sequence-to-sequence model
Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improving the Performance of Online Neural Transducer Models
Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (LAS).
Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
However, there has been little previous work comparing phoneme-based versus grapheme-based sub-word units in the end-to-end modeling framework, to determine whether the gains from such approaches are primarily due to the new probabilistic model, or from the joint learning of the various components with grapheme-based units.
State-of-the-art Speech Recognition With Sequence-to-Sequence Models
Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models
We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components.
On the efficient representation and execution of deep acoustic models
In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values.
On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition
We study the problem of compressing recurrent neural networks (RNNs).
Personalized Speech recognition on mobile devices
We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone.
