Tootfinder

"As a political force, the Labour left is finished. The tactic of entryism – entering the Labour party and changing it – is finished too."
"..a string of local council victories next year would pave the way for an unprecedented challenge to #Labour – not from the right, as the party has always had to fight, but from its radical flank. And this new movement could take parts of Lab…

The British left is coming for the Government
Whisper it as yet, but after five long years of confusion and disarray, the British left is rallying. Local political organisations are coalescing, from Chiswick to Liverpool to Newcastle. The Green P

🇺🇦 #NowPlaying on KEXP's #AfternoonShow
Wham!:
🎵 Careless Whisper
#Wham
https://thepillarsofcreation.bandcamp.com/track/wham-careless-whisper-the-pillars-of-creation-remix
https://open.spotify.com/track/5ffN26rI0YkSS4t6M63oez

Series C, Episode 07 - Children of Auron
C.A. TWO: Next, the young adults. Thank you, module six.
C.A. ONE: Any response to the distress calls?
C.A. TWO: Not a whisper. Appeals out on all channels, nothing.
VOICE: Medical section reporting.
https://blake.torpidity.net/m/307/119

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Hands-on with Apple's new Speech framework components in the macOS Tahoe beta: the APIs deliver transcription speeds significantly faster than OpenAI's Whisper (John Voorhees/MacStories)
https://www.macstories.net/stories/hands-o…

Hands-On: How Apple’s New Speech APIs Outpace Whisper for Lightning-Fast Transcription
Late last Tuesday night, after watching F1: The Movie at the Steve Jobs Theater, I was driving back from dropping Federico off at his hotel when I got a text: Can you pick me up? It was from my son Finn, who had spent the evening nearby and was stalking me in Find My. Of

"Geothermal energy keeps utility bills low in this Texas neighborhood"
#US #USA #America #Energy

Geothermal energy keeps utility bills low in this Texas neighborhood
The development outside Austin taps into natural heat deep underground to run heating and cooling systems for the planned 7,500 homes and other buildings.

Series C, Episode 07 - Children of Auron
C.A. TWO: Next, the young adults. Thank you, module six.
C.A. ONE: Any response to the distress calls?
C.A. TWO: Not a whisper. Appeals out on all channels, nothing.
VOICE: Medical section reporting.
https://blake.torpidity.net/m/307/119

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
Haoran Zhou, Xingchen Song, Brendan Fahy, Qiaochu Song, Binbin Zhang, Zhendong Peng, Anshul Wadhawan, Denglin Jiang, Apurv Verma, Vinay Ramesh, Srivas Prasad, Michele M. Franceschini
https://arxiv.org/abs/2506.12154 …

Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming ASR. In this paper, we fine-tune Whisper for streaming ASR using the WeNet toolkit by adopting a Unified Two-pass (U2) structure. We introduce an additional Connectionist Temporal Classification (CTC) decoder trained with causal attention masks to generate str…

This https://arxiv.org/abs/2505.21527 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
Automatic speech recognition (ASR) has made remarkable progress but heavily relies on large-scale labeled data, which is scarce for low-resource languages like Vietnamese. While existing systems such as Whisper, USM, and MMS achieve promising performance, their efficacy remains inadequate in terms of training costs, latency, and accessibility. To address these issues, we propose VietASR, a novel ASR training pipeline that leverages vast amounts of unlabeled data and a small set of labeled data.…

A. I wonder what language the French pres. uses to whisper to the Italian pres?
B. How does Meloni manage to dress like a 12 year old girl and somehow not seem ridiculous?
C. Feel the stomach acid the Japanese delegate is experiencing 😬
D. How is it that Starmer manages to look *exactly* as awkward at these meetings as Theresa May did?

Not a whisper about this on DR's news site so thanks 🙏 @… for sharing the original briefing.
Looking forward to better IT support on our Linux machines now...
https://mastodon.social/@randahl/114655674138180496
randahl@mastodon.social - In Denmark, The Ministry of Digitalization now removes all Microsoft software from ministry computers and switches to open source in a strategy that has been agreed with all five regions of Denmark.
The more Trump threatens Europe, the more US companies will get the Tesla treatment.
I will not be surprised if the Parliament member iPhones are next.
https://nordjyske.dk/nyheder/politik/digitaliseringsminister-vil-udfase-microsoft-i-sit-eget-ministerium/5616096

Exploiting Music Source Separation for Automatic Lyrics Transcription with Whisper
Jaza Syed, Ivan Meresman Higgs, Ond\v{r}ej C\'ifka, Mark Sandler
https://arxiv.org/abs/2506.15514

Exploiting Music Source Separation for Automatic Lyrics Transcription with Whisper
Automatic lyrics transcription (ALT) remains a challenging task in the field of music information retrieval, despite great advances in automatic speech recognition (ASR) brought about by transformer-based architectures in recent years. One of the major challenges in ALT is the high amplitude of interfering audio signals relative to conventional ASR due to musical accompaniment. Recent advances in music source separation have enabled automatic extraction of high-quality separated vocals, which c…

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
Yui Sudo, Yusuke Fujita, Atsushi Kojima, Tomoya Mizumoto, Lianbo Liu
https://arxiv.org/abs/2506.09448

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words. While contextual biasing (CB) is a promising approach to improve recognition of such words, most CB methods are trained from scratch, resulting in lower performance than SFMs due to the lack of pre-trained knowledge. This paper integrates an existing CB method…

Series A, Episode 12 - Deliverance
BLAKE: I don't know. They look like micro power cells.
CALLY: I've never seen that type before.
ENSOR: [Strangled whisper] Help...help...help me. Help me.
https://blake.torpidity.net/m/112/144 B7B5

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
Aref Farhadipour, Homayoon Beigi, Volker Dellwo, Hadi Veisi
https://arxiv.org/abs/2506.16969

State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
Whispered speech recognition presents significant challenges for conventional automatic speech recognition systems, particularly when combined with dialect variation. However, utilizing an efficient method to solve this problem using a low-range dataset and processing load is beneficial. This paper proposes a solution using a Mamba-based state-space model and four fine-tuned self-supervised models consisting of Wav2Vec2, WavLM, HuBERT, and Whisper to address the dual challenges of whispered spe…

Improving Code Switching with Supervised Fine Tuning and GELU Adapters
Linh Pham
https://arxiv.org/abs/2506.00291 https://arxiv.org/p…

Improving Code Switching with Supervised Fine Tuning and GELU Adapters
There are few code switching datasets, labeled or unlabled, that exist today. As a result, ASR requires new methods to utilize the vast monolingual data and models that exist. This paper uses OpenAI's open source ASR model, Whisper, which has been pre-trained on 680K hours of audio to perform monolingual ASR tasks. In Part 1, this paper examines how exploiting Whisper's monolingual ability to individually tokenize training text, called "Switching Tokenizers Method", improves transcription accur…

This https://arxiv.org/abs/2501.16344 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning
Current speech encoding pipelines often rely on an additional text-based LM to get robust representations of human communication, even though SotA speech-to-text models often have a LM within. This work proposes an approach to improve the LM within an audio model such that the subsequent text-LM is unnecessary. We introduce WhiSPA (Whisper with Semantic and Psychological Alignment), which leverages a novel audio training objective: contrastive loss with a language model embedding as a teacher. …

BUT System for the MLC-SLM Challenge
Alexander Polok, Jiangyu Han, Dominik Klement, Samuele Cornell, Jan \v{C}ernock\'y, Luk\'a\v{s} Burget
https://arxiv.org/abs/2506.13414

BUT System for the MLC-SLM Challenge
We present a two-speaker automatic speech recognition (ASR) system that combines DiCoW -- a diarization-conditioned variant of Whisper -- with DiariZen, a diarization pipeline built on top of Pyannote. We first evaluate both systems in out-of-domain (OOD) multilingual scenarios without any fine-tuning. In this scenario, DiariZen consistently outperforms the baseline Pyannote diarization model, demonstrating strong generalization. Despite being fine-tuned on English-only data for target-speaker …

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Jakaria Islam Emon, Kazi Tamanna Alam, Md. Abu Salek
https://arxiv.org/abs/2506.05899

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for…

Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts
Lingyun Gao, Cristian Tejedor-Garcia, Catia Cucchiarini, Helmer Strik
https://arxiv.org/abs/2506.11079

Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts
Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel multimodal approach that leverages audio and knowledge from text resources. In particular, we explored the potential of using Whisper and instruction-tuned large language models (LLMs) with prompts to improve transcriptions for child speech recognition, as well as …

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
https://arxiv.org/abs/2506.01365

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that …

Joint ASR and Speaker Role Tagging with Serialized Output Training
Anfeng Xu, Tiantian Feng, Shrikanth Narayanan
https://arxiv.org/abs/2506.10349 https://

Joint ASR and Speaker Role Tagging with Serialized Output Training
Automatic Speech Recognition systems have made significant progress with large-scale pre-trained models. However, most current systems focus solely on transcribing the speech without identifying speaker roles, a function that is critical for conversational AI. In this work, we investigate the use of serialized output training (SOT) for joint ASR and speaker role tagging. By augmenting Whisper with role-specific tokens and fine-tuning it with SOT, we enable the model to generate role-aware trans…

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
Chen Bao, Chuanbing Huo, Qinyu Chen, Chang Gao
https://arxiv.org/abs/2506.06566

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically combines standard and aphasic speech at varying ratios, enabling robust generalization, and a GPT-4-based reference enhancement method that refines noisy aphasic transcripts, improving supervision quality. We conduct extensive experiments across multiple data mix…

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Karl El Hajal, Enno Hermann, Sevada Hovsepyan, Mathew Magimai. -Doss
https://arxiv.org/abs/2506.01618 …

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiment…