Related papers: Residual Energy-Based Models for End-to-End Speech…
End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse…
Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving…
Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition (ASR) systems. In many applications, it is of interest to estimate WER given a pair of a speech utterance and a…
We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the…
In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually trained to maximize the likelihood of correct word…
We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version. Attractor networks provide a sound model of associative memory: patterns are stored…
Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, creating a public…
This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…
In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker…
Segmental models are sequence prediction models in which scores of hypotheses are based on entire variable-length segments of frames. We consider segmental models for whole-word ("acoustic-to-word") speech recognition, with the feature…
In indoor scenes, reverberation is a crucial factor in degrading the perceived quality and intelligibility of speech. In this work, we propose a generative dereverberation method. Our approach is based on a probabilistic model utilizing a…
Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems,…
On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…
The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…
Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious…
While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult…
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data.…
While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…
Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…
Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…