Related papers: SARG: A Novel Semi Autoregressive Generator for Mu…

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However, while AR…

Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries…

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still…

Recently, autoregressive (AR) language models have emerged as a dominant approach in speech synthesis, offering expressive generation and scalable training. However, conventional AR speech synthesis models relying on the next-token…

Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations…

A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn…

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation…

We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks containing over 2,800 conversation turns across 6…

Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. In this…

Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…

We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions, which augments a query through text generation of heuristically discovered relevant contexts without external resources as supervision. We demonstrate that…

We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation.…

Singing Accompaniment Generation (SAG), which generates instrumental music to accompany input vocals, is crucial to developing human-AI symbiotic art creation systems. The state-of-the-art method, SingSong, utilizes a multi-stage…

Retrieval-Augmented Generation has made significant progress in the field of natural language processing. By combining the advantages of information retrieval and large language models, RAG can generate relevant and contextually appropriate…

We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a…

Applying speech super-resolution (SR) to recordings with severely low sampling rates is a critical challenge in digital archiving and investigative audio recovery. In these scenarios, the input lacks essential acoustic cues. Consequently,…

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically…

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is…

Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…