相关论文: Average Token Delay: A Latency Metric for Simultan…

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Automatic dubbing (AD) is among the machine translation (MT) use cases where translations should match a given length to allow for synchronicity between source and target speech. For neural MT, generating translations of length close to the…

Measuring the in-context computational effort of language models is a key challenge, as metrics like next-token loss fail to capture reasoning complexity. Prior methods based on latent state compressibility can be invasive and unstable. We…

The high-quality translation results produced by machine translation (MT) systems still pose a huge challenge for automatic evaluation. Current MT evaluation pays the same attention to each sentence component, while the questions of…

CTC-based streaming ASR has gained significant attention in real-world applications but faces two main challenges: accuracy degradation in small chunks and token emission latency. To mitigate these challenges, we propose Delayed-KD, which…

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs…

Simultaneous translation involves translating a sentence before the speaker's utterance is completed in order to realize real-time understanding in multiple languages. This task is significantly more challenging than the general full…

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Simultaneous interpretation, the translation of speech from one language to another in real-time, is an inherently difficult and strenuous task. One of the greatest challenges faced by interpreters is the accurate translation of difficult…

Simultaneous translation (ST) outputs translation while receiving the source inputs, and hence requires a policy to determine whether to translate a target token or wait for the next source token. The major challenge of ST is that each…

As machine translation (MT) metrics improve their correlation with human judgement every year, it is crucial to understand the limitations of such metrics at the segment level. Specifically, it is important to investigate metric behaviour…

Recent machine translation (MT) metrics calibrate their effectiveness by correlating with human judgement but without any insights about their behaviour across different error types. Challenge sets are used to probe specific dimensions of…

Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to automatically evaluate speech-to-speech translation is an open question which has…

Automatic dubbing (AD) is the task of translating the original speech in a video into target language speech. The new target language speech should satisfy isochrony; that is, the new speech should be time aligned with the original video,…

Simultaneous machine translation (SiMT) outputs the translation while receiving the source inputs, and hence needs to balance the received source information and translated target information to make a reasonable decision between waiting…

This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad…

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…

Simultaneous machine translation (SimulMT) presents a challenging trade-off between translation quality and latency. Recent studies have shown that LLMs can achieve good performance in SimulMT tasks. However, this often comes at the expense…

In this paper, we propose a new algorithm for the estimation of multiple time delays (TDs). Since a TD is a fundamental spatial cue for sensor array signal processing techniques, many methods for estimating it have been studied. Most of…