Textually pretrained speech language models
Speech language models (SpeechLMs) process and generate acoustic data only, without
textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using …
textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using …
Audiobox: Unified audio generation with natural language prompts
Audio is an essential part of our life, but creating it often requires expertise and is time-
consuming. Research communities have made great progress over the past year advancing …
consuming. Research communities have made great progress over the past year advancing …
Recent advances in speech language models: A survey
Large Language Models (LLMs) have recently garnered significant attention, primarily for
their capabilities in text-based interactions. However, natural human interaction often relies …
their capabilities in text-based interactions. However, natural human interaction often relies …
SUMMEDITS: measuring LLM ability at factual reasoning through the lens of summarization
With the recent appearance of LLMs in practical settings, having methods that can effectively
detect factual inconsistencies is crucial to reduce the propagation of misinformation and …
detect factual inconsistencies is crucial to reduce the propagation of misinformation and …
Llms as factual reasoners: Insights from existing benchmarks and beyond
With the recent appearance of LLMs in practical settings, having methods that can effectively
detect factual inconsistencies is crucial to reduce the propagation of misinformation and …
detect factual inconsistencies is crucial to reduce the propagation of misinformation and …
Computational sociophonetics using automatic speech recognition
R Coto‐Solano - Language and Linguistics Compass, 2022 - Wiley Online Library
Recent years have seen numerous advances in natural language processing that can help
accelerate sociophonetic work. These include software to align speech recordings with their …
accelerate sociophonetic work. These include software to align speech recordings with their …
Audio summarization for podcasts
We propose a novel system to automatically generate audio summaries for podcasts,
allowing listeners to quickly preview podcast episodes. The proposed system first …
allowing listeners to quickly preview podcast episodes. The proposed system first …
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach
to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a …
to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a …
A two-phase approach for abstractive podcast summarization
Podcast summarization is different from summarization of other data formats, such as news,
patents, and scientific papers in that podcasts are often longer, conversational, colloquial …
patents, and scientific papers in that podcasts are often longer, conversational, colloquial …
Towards proactive information retrieval in noisy text with Wikipedia concepts
T Ahmed, S Bulathwela - arXiv preprint arXiv:2210.09877, 2022 - arxiv.org
Extracting useful information from the user history to clearly understand informational needs
is a crucial feature of a proactive information retrieval system. Regarding understanding …
is a crucial feature of a proactive information retrieval system. Regarding understanding …