Related papers: Learning a Neural Diff for Speech Models

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

Scaling neural network models has delivered dramatic quality gains across ML problems. However, this scaling has increased the reliance on efficient distributed training techniques. Accordingly, as with other distributed computing…

When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models. The availability of pre-trained models is a promising…

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language…

We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…

Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised…

Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…

The evaluation of synthetic and processed speech has long been a cornerstone of audio engineering and speech science. Although subjective listening tests remain the gold standard for assessing perceptual quality and intelligibility, their…

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…

The differences in written text and conversational speech are substantial; previous parsers trained on treebanked text have given very poor results on spontaneous speech. For spoken language, the mismatch in style also extends to prosodic…

The conventional wisdom has been that designing ultra-compact, battery-constrained wireless hearables with on-device speech AI models is challenging due to the high computational demands of streaming deep learning models. Speech AI models…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…