Related papers: R-BI: Regularized Batched Inputs enhance Increment…
Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as…
End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…
Speculative sampling is a promising approach to accelerate the decoding stage for Large Language Models (LLMs). Recent advancements that leverage target LLM's contextual information, such as hidden states and KV cache, have shown…
Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
For spoken language translation (SLT) in live scenarios such as conferences, lectures and meetings, it is desirable to show the translation to the user as quickly as possible, avoiding an annoying lag between speaker and translated…
Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…
This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…
Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…
This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…
We present a modular approach to building cascade speech translation (AST) models that guarantees that the resulting model performs no worse than the 1-best cascade baseline while preserving state-of-the-art speech recognition (ASR) and…
With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…
This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include…
The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…
Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…
Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…
Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT)…
The paper describes BUT's English to German offline speech translation(ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on…
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…
Many recent approaches to structured NLP tasks use an autoregressive language model $M$ to map unstructured input text $x$ to output text $y$ representing structured objects (such as tuples, lists, trees, code, etc.), where the desired…