AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers introduce HALAS, the first human-annotated dataset documenting naturally occurring hallucinations from seven state-of-the-art ASR systems on real earnings call recordings. The benchmark reveals that hallucinations persist even in nearly correct transcriptions and establishes rigorous evaluation methods, with current detection techniques achieving only 53.1% F1 scores despite character-level metrics reaching 81% ROC-AUC.
AIBullishCrypto Briefing · Jun 237/10
🧠OpenAI is developing the GPT-Bidi-1 model designed to enhance ChatGPT's voice capabilities with improved real-time conversational fluidity and adaptability. This advancement represents a significant upgrade to AI voice interaction technology that could reshape how users engage with conversational AI systems.
🏢 OpenAI🧠 ChatGPT
AIBullisharXiv – CS AI · Jun 107/10
🧠Whisfusion introduces a masked diffusion decoder that achieves faster speech-to-text processing than Whisper-large-v3 while matching or exceeding its accuracy across multilingual benchmarks. By replacing autoregressive decoding with parallel diffusion decoding, the system runs 4-5x faster while maintaining competitive performance with leading ASR systems, establishing non-autoregressive diffusion as a viable paradigm for high-throughput transcription.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers present FormalASR, compact end-to-end models that convert spoken Chinese directly into formal written text, eliminating the need for post-processing with large language models. Built on newly created datasets and fine-tuned versions of Qwen3-ASR, the solution achieves significant error reduction while enabling lightweight on-device deployment.
AIBearisharXiv – CS AI · Jun 87/10
🧠Researchers demonstrate a new adversarial attack called Semantic Gambit that exploits Large Language Models to significantly compromise real-time Automatic Speech Recognition systems. By leveraging predictive context from LLMs, the attack achieves a 35.6% Word Error Rate—three times higher than previously documented attacks—revealing a critical vulnerability in ASR pipelines that operate under temporal constraints.
AIBullisharXiv – CS AI · Jun 87/10
🧠Researchers demonstrate that Whisper, OpenAI's widely-used speech recognition model, can detect and mitigate hallucinations—fabricated coherent transcriptions from non-speech audio—using Sparse AutoEncoders and activation-space steering. The approach reduces hallucination rates from 72-87% to 14-27% across model sizes with minimal performance degradation on actual speech.
AIBearisharXiv – CS AI · Jun 57/10
🧠Researchers have developed a new adversarial attack method against automatic speech recognition systems that operates in feature space rather than directly on audio waveforms, achieving significantly higher transfer rates to black-box ASR models and bypassing existing defenses. The attack uses self-supervised learning representations and vocoders to reconstruct adversarial signals, revealing critical vulnerabilities in current ASR robustness evaluation protocols.
AIBullisharXiv – CS AI · Jun 47/10
🧠Researchers introduce Audio-Interaction, a unified streaming model that enables Large Audio Language Models to process audio in real time through a perceive-decide-respond loop, handling tasks from speech recognition to voice chatting. The framework, SoundFlow, includes a new 2.6M-item streaming corpus and demonstrates competitive performance on mainstream audio tasks while unlocking real-time interactive capabilities previously unavailable to offline models.
AIBullisharXiv – CS AI · Jun 27/10
🧠MOSS-Audio is a unified audio-language model supporting speech, environmental sound, and music understanding with capabilities in captioning, question answering, and temporal grounding. The model introduces DeepStack cross-layer feature injection and time markers for explicit temporal cues, released in 4B and 8B variants for instruction-following and reasoning tasks.
AIBullisharXiv – CS AI · Jun 27/10
🧠Researchers propose ASKD-Whisper, a new knowledge distillation technique that compresses OpenAI's Whisper speech recognition model while improving performance. The method achieves 5x faster inference and 1.07% lower error rates than the original teacher model by dynamically reducing reliance on the teacher's predictions during training.
AIBullisharXiv – CS AI · May 297/10
🧠HoliTok is a new continuous speech tokenization model that unifies speech generation and understanding tasks by encoding 48kHz audio into compact 128-dimensional latent sequences at 25Hz. The breakthrough addresses a key challenge in building unified speech foundation models by creating a tokenization space that balances reconstruction fidelity, semantic preservation, and learnability without requiring architectural workarounds.
AIBearisharXiv – CS AI · May 297/10
🧠Researchers have developed a comprehensive taxonomy of jailbreak attacks and defenses for Large Audio Language Models (LALMs), identifying vulnerabilities across semantic, acoustic, signal, and embedding layers. The study reveals that current defenses create tradeoffs between robustness and usability, highlighting the need for cost-aware safety evaluation beyond simple success-rate metrics.
AIBullishDecrypt – AI · May 267/10
🧠StepFun, a Shanghai-based AI lab known for developing efficient large language models, has achieved top benchmark results in voice AI technology with notable sensitivity to acoustic nuances like sighs. The breakthrough demonstrates the lab's capability to extend its LLM expertise into multimodal AI, potentially reshaping voice recognition and AI assistant markets.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers introduce WorldSpeech, a multilingual speech corpus containing 65,000 hours of aligned audio-transcript data across 76 languages, addressing the critical gap in ASR training data for low-resource languages. Fine-tuning existing ASR models on this dataset achieves an average 63.5% relative Word-Error-Rate reduction, significantly improving speech recognition accuracy for underrepresented languages.
AIBullishOpenAI News · May 77/10
🧠OpenAI has introduced new realtime voice models in its API that enable advanced capabilities including reasoning, translation, and speech transcription. These models represent a significant step toward more natural and intelligent voice-based interactions, expanding the practical applications available to developers building voice-enabled applications.
🏢 OpenAI
AIBullisharXiv – CS AI · Mar 277/10
🧠Ming-Flash-Omni is a new 100 billion parameter multimodal AI model with Mixture-of-Experts architecture that uses only 6.1 billion active parameters per token. The model demonstrates unified capabilities across vision, speech, and language tasks, achieving performance comparable to Gemini 2.5 Pro on vision-language benchmarks.
🧠 Gemini
AIBullisharXiv – CS AI · Mar 267/10
🧠Alberta Health Services deployed Berta, an open-source AI scribe platform that reduces clinical documentation costs by 70-95% compared to commercial alternatives. The system was used by 198 emergency physicians across 105 facilities, generating over 22,000 clinical sessions while keeping all data within secure health system infrastructure.
AIBearisharXiv – CS AI · Mar 177/10
🧠Researchers developed SWhisper, a framework that uses near-ultrasonic audio to deliver covert jailbreak attacks against speech-driven AI systems. The technique is inaudible to humans but can successfully bypass AI safety measures with up to 94% effectiveness on commercial models.
AIBullisharXiv – CS AI · Mar 37/103
🧠Researchers have released WAXAL, a large-scale multilingual speech dataset covering 24 Sub-Saharan African languages representing over 100 million speakers. The dataset includes 1,250 hours of transcribed speech for ASR and 235 hours of high-quality recordings for TTS, released under CC-BY-4.0 license to advance inclusive AI technologies.
AIBullishMIT News – AI · Dec 57/106
🧠MIT researchers have developed a speech-to-reality system that combines 3D generative AI with robotic assembly to create physical objects on demand from voice commands. The technology represents a significant advancement in AI-driven manufacturing and automation capabilities.
AIBullishOpenAI News · Apr 247/106
🧠OpenAI has released APIs for ChatGPT and Whisper models, allowing developers to integrate these AI capabilities directly into their applications and products. This marks a significant step in making advanced conversational AI and speech recognition technology accessible to third-party developers.
AIBullishOpenAI News · Sep 217/107
🧠OpenAI has trained and open-sourced Whisper, a neural network for speech recognition that achieves human-level robustness and accuracy on English speech. The model represents a significant advancement in AI speech recognition technology and is being made freely available to the community.
AINeutralarXiv – CS AI · Jun 255/10
🧠Researchers developed an AI-powered screening tool for detecting speech sound errors in Polish-speaking children, using wav2vec2 technology to identify sibilant substitutions. The system achieves 88.7% accuracy on a test set and demonstrates 72.9% precision with a 2.7% false-alarm rate, designed as a lightweight alternative to specialist evaluation for early intervention.
AIBullisharXiv – CS AI · Jun 256/10
🧠Researchers propose an error-aware TF-IDF retrieval-augmented generation framework that corrects automatic speech recognition (ASR) errors by using phonetically-aware lexical matching rather than heavy cross-modal embeddings. The method achieved a 37.2 percentage-point improvement in error-aware hit rate and reduced word error rate by 4.23 points on Persian speech data with minimal computational overhead.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce DSSCNet, a deep learning framework using transfer learning to improve dysarthric speech severity classification across different datasets. The model achieves 75.80% accuracy on TORGO and 68.25% on UA-Speech corpora, demonstrating significant improvements in speaker-independent assessment and cross-corpus generalization for assistive speech technologies.
