Talking to Robots: A Practical Examination of Speech Foundation Models for HRI Applications

Automatic Speech Recognition (ASR) systems in real-world settings need to handle imperfect audio, often degraded by hardware limitations or environmental noise, while accommodating diverse user groups. In human-robot interaction (HRI), these challenges intersect to create a uniquely challenging recognition environment. We evaluate four state-of-the-art ASR systems on eight publicly available datasets that capture six dimensions of difficulty: domain-specific, accented, noisy, age-variant, impaired, and spontaneous speech. Our analysis demonstrates significant variations in performance, hallucination tendencies, and inherent biases, despite similar scores on standard benchmarks. These limitations have serious implications for HRI, where recognition errors can interfere with task performance, user trust, and safety.

Pitch Accent Detection improves Pretrained Automatic Speech Recognition

We show the performance of Automatic Speech Recognition (ASR) systems that use semi-supervised speech representations can be boosted by a complimentary pitch accent detection module, by introducing a joint ASR and pitch accent detection model. The pitch accent detection component of our model achieves a significant improvement on the state-of-the-art for the task, closing the gap in F1-score by 41%. Additionally, the ASR performance in joint training decreases WER by 28.3% on LibriSpeech, under limited resource fine-tuning. With these results, we show the importance of extending pretrained speech models to retain or re-learn important prosodic cues such as pitch accent.

A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation

Automatic Speech Recognition (ASR) has become an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the inherent variability of human speech, such as accents, dialects, and speaking styles, as well as environmental interference, including background noise. Moreover, domain-specific conversations often employ specialized terminology, which can exacerbate transcription errors. These shortcomings not only degrade raw ASR accuracy but also propagate mistakes through subsequent natural language processing pipelines. Because redesigning an ASR model is costly and time-consuming, non-intrusive refinement techniques that leave the model's architecture unchanged have become increasingly popular. In this survey, we systematically review current non-intrusive refinement approaches and group them into five classes: fusion, re-scoring, correction, distillation, and training adjustment. For each class, we outline the main methods, advantages, drawbacks, and ideal application scenarios. Beyond method classification, this work surveys adaptation techniques aimed at refining ASR in domain-specific contexts, reviews commonly used evaluation datasets along with their construction processes, and proposes a standardized set of metrics to facilitate fair comparisons. Finally, we identify open research gaps and suggest promising directions for future work. By providing this structured overview, we aim to equip researchers and practitioners with a clear foundation for developing more robust, accurate ASR refinement pipelines.

Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition

We aim to improve the robustness of Automatic Speech Recognition (ASR) systems against non-native speech, particularly in low-resourced multi-accent settings. We introduce Mixture of Accent-Specific LoRAs (MAS-LoRA), a fine-tuning method that leverages a mixture of Low-Rank Adaptation (LoRA) experts, each specialized in a specific accent. This method can be used when the accent is known or unknown at inference time, without the need to fine-tune the model again. Our experiments, conducted using Whisper on the L2-ARCTIC corpus, demonstrate significant improvements in Word Error Rate compared to regular LoRA and full fine-tuning when the accent is unknown. When the accent is known, the results further improve. Furthermore, MAS-LoRA shows less catastrophic forgetting than the other fine-tuning methods. To the best of our knowledge, this is the first use of a mixture of LoRA experts for non-native multi-accent ASR.

Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in self-supervised learning have shown that self-supervised pre- training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios. We aim to investigate the effectiveness of this paradigm for Chinese dialects. Specifically, we pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data and do alignment training on a supervised dataset of 40,000 hours. Then, we systematically examine the impact of various projectors and LLMs on Mandarin, dialect, and accented speech recognition performance under this paradigm. Our method achieved SOTA results on multiple dialect datasets, including Kespeech. We will open-source our work to promote reproducible research

Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR

To build an automatic speech recognition (ASR) system that can serve everyone in the world, the ASR needs to be robust to a wide range of accents including unseen accents. We systematically study how three different variables in training data -- the number of speakers, the audio duration per each individual speaker, and the diversity of accents -- affect ASR robustness towards unseen accents in a low-resource training regime. We observe that for a fixed number of ASR training hours, it is more beneficial to increase the number of speakers (which means each speaker contributes less) than the number of hours contributed per speaker. We also observe that more speakers enables ASR performance gains from scaling number of hours. Surprisingly, we observe minimal benefits to prioritizing speakers with different accents when the number of speakers is controlled. Our work suggests that practitioners should prioritize increasing the speaker count in ASR training data composition for new languages.

Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora

Recently, a method for synthesizing foreign-accented speech only with native speech data using discrete tokens obtained from self-supervised learning (SSL) models was proposed. Considering limited availability of accented speech data, this method is expected to make it much easier to simulate foreign accents. By using the synthesized accented speech as listening materials for humans or training data for automatic speech recognition (ASR), both of them will acquire higher robustness against foreign accents. However, the previous method has a fatal flaw that it cannot reproduce duration-related accents. Durational accents are commonly seen when L2 speakers, whose native language has syllable-timed or mora-timed rhythm, speak stress-timed languages, such as English. In this paper, we integrate duration modification to the previous method to simulate foreign accents more accurately. Experiments show that the proposed method successfully replicates durational accents seen in real L2 speech.

Inclusivity of AI Speech in Healthcare: A Decade Look Back

The integration of AI speech recognition technologies into healthcare has the potential to revolutionize clinical workflows and patient-provider communication. However, this study reveals significant gaps in inclusivity, with datasets and research disproportionately favouring high-resource languages, standardized accents, and narrow demographic groups. These biases risk perpetuating healthcare disparities, as AI systems may misinterpret speech from marginalized groups. This paper highlights the urgent need for inclusive dataset design, bias mitigation research, and policy frameworks to ensure equitable access to AI speech technologies in healthcare.

PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems

Although Automatic Speech Recognition (ASR) systems have become an integral part of modern technology, their evaluation remains challenging, particularly for low-resource languages such as Persian. This paper introduces Persian Speech Recognition Benchmark(PSRB), a comprehensive benchmark designed to address this gap by incorporating diverse linguistic and acoustic conditions. We evaluate ten ASR systems, including state-of-the-art commercial and open-source models, to examine performance variations and inherent biases. Additionally, we conduct an in-depth analysis of Persian ASR transcriptions, identifying key error types and proposing a novel metric that weights substitution errors. This metric enhances evaluation robustness by reducing the impact of minor and partial errors, thereby improving the precision of performance assessment. Our findings indicate that while ASR models generally perform well on standard Persian, they struggle with regional accents, children's speech, and specific linguistic challenges. These results highlight the necessity of fine-tuning and incorporating diverse, representative training datasets to mitigate biases and enhance overall ASR performance. PSRB provides a valuable resource for advancing ASR research in Persian and serves as a framework for developing benchmarks in other low-resource languages. A subset of the PSRB dataset is publicly available at https://huggingface.co/datasets/PartAI/PSRB.

Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use

Automatic speech recognition (ASR) research is driven by the availability of common datasets between industrial researchers and academics, encouraging comparisons and evaluations. LibriSpeech, despite its long success as an ASR benchmark, is now limited by its size and focus on clean, read speech, leading to near-zero word error rates. More recent datasets, including MOSEL, YODAS, Gigaspeech, OWSM, Libriheavy or People's Speech suffer from major limitations including licenses that researchers in the industry cannot use, unreliable transcriptions, incorrect audio data, or the lack of evaluation sets. This work presents the Loquacious Set, a 25,000-hour curated collection of commercially usable English speech. Featuring hundreds of thousands of speakers with diverse accents and a wide range of speech types (read, spontaneous, talks, clean, noisy), the Loquacious Set is designed to work for academics and researchers in the industry to build ASR systems in real-world scenarios.