Mengjie Qian

Erfan Loweimi, Mengjie Qian, Kate Knill et al.

When retrieving a person from a video archive by voice and face, should the system be multimodal or not? In real-world broadcast archives, unlike curated benchmarks, a target may be heard but unseen, seen but unheard, or both. Fusing scores from an absent modality injects noise, degrading precision below the best unimodal system. We propose a query-adaptive framework that detects active modalities via cross-modal score consistency: when both modalities are active, files retrieved by one also score highly on the other; this agreement breaks down when a modality is absent. Classifiers driven by these cross-modal features achieve 89% detection accuracy. On the BBC Rewind corpus (with over 12,000 broadcast videos) the adaptive system attains 94.2% P@1, outperforming speaker-only (82.9%), face-only (93.4%), and fixed fusion (90.0%), recovering 64% of the gap to an oracle with ground-truth modality labels (96.6%).

Rao Ma, Mengjie Qian, Potsawee Manakul et al.

ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using the decoding results of a target ASR system. This approach can be computationally intensive and the model is tuned to a specific ASR system. Recently generative large language models (LLMs) have been applied to a wide range of natural language processing tasks, as they can operate in a zero-shot or few shot fashion. In this paper we investigate using ChatGPT, a generative LLM, for ASR error correction. Based on the ASR N-best output, we propose both unconstrained and constrained, where a member of the N-best list is selected, approaches. Additionally, zero and 1-shot settings are evaluated. Experiments show that this generative LLM approach can yield performance gains for two different state-of-the-art ASR architectures, transducer and attention-encoder-decoder based, and multiple test sets.

Rao Ma, Mark J. F. Gales, Kate M. Knill et al.

Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use the 1-best ASR hypothesis as input and therefore can only perform correction by leveraging the context within one sentence. In this work, we propose a novel N-best T5 model for this task, which is fine-tuned from a T5 model and utilizes ASR N-best lists as model input. By transferring knowledge from the pre-trained language model and obtaining richer information from the ASR decoding space, the proposed approach outperforms a strong Conformer-Transducer baseline. Another issue with standard error correction is that the generation process is not well-guided. To address this a constrained decoding process, either based on the N-best list or an ASR lattice, is used which allows additional information to be propagated.

Mengjie Qian, Rao Ma, Adian Liusie et al. · cambridge

Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content, topic, and emotion. A key element for this process is highly rapid and flexible search to support large archives, which in MVSE is facilitated by representing video attributes with embeddings. This work aims to compensate for any performance loss from this rapid archive search by examining reranking approaches. In particular, zero-shot reranking methods using large language models (LLMs) are investigated as these are applicable to any video archive audio content. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus. Results demonstrate that reranking significantly improves retrieval ranking without requiring any task-specific in-domain training data. Furthermore, three sources of information (ASR transcriptions, automatic summaries and synopses) as input for LLM reranking were compared. To gain a deeper understanding and further insights into the performance differences and limitations of these text sources, we employ a fact-checking approach to analyse the information consistency among them.

Rao Ma, Mengjie Qian, Mark J. F. Gales et al.

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is designed to be human readable, punctuation is added, numbers are presented in Arabic numeric form and abbreviations are included. Additionally, these models have a tendency to skip disfluencies and hesitations in the output. Though useful for readability, these attributes are not helpful for assessing the ability of a candidate and providing feedback. Here a precise transcription of what a candidate said is needed. In this paper, we give a detailed analysis of Whisper outputs and propose two solutions: fine-tuning and soft prompt tuning. Experiments are conducted on both public speech corpora and an English learner dataset. Results show that we can effectively alter the decoding behaviour of Whisper to generate the exact words spoken in the response.

Mengjie Qian, Siyuan Tang, Rao Ma et al.

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language set. Fine-tuning, while simple, may degrade the accuracy of the original set. We compare three approaches that exploit adaptation parameters: soft language code tuning, train only the language code; soft prompt tuning, train prepended tokens; and LoRA where a small set of additional parameters are optimised. Elastic Weight Consolidation (EWC) offers an alternative compromise with the potential to maintain performance in specific target languages. Results show that direct fine-tuning yields the best performance for the new language but degrades existing language capabilities. EWC can address this issue for specific languages. If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language.

Stefano Bannò, Rao Ma, Mengjie Qian et al.

Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar when speaking. This process usually relies on a cascaded pipeline comprising an ASR system, disfluency removal, and GEC, with the associated concern of propagating errors between these individual modules. In this paper, we introduce an alternative "end-to-end" approach to spoken GEC, exploiting a speech recognition foundation model, Whisper. This foundation model can be used to replace the whole framework or part of it, e.g., ASR and disfluency removal. These end-to-end approaches are compared to more standard cascaded approaches on the data obtained from a free-speaking spoken language assessment test, Linguaskill. Results demonstrate that end-to-end spoken GEC is possible within this architecture, but the lack of available data limits current performance compared to a system using large quantities of text-based GEC data. Conversely, end-to-end disfluency detection and removal, which is easier for the attention-based Whisper to learn, does outperform cascaded approaches. Additionally, the paper discusses the challenges of providing feedback to candidates when using end-to-end systems for spoken GEC.

Rao Ma, Mengjie Qian, Mark J. F. Gales et al.

As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than having direct access to models themselves. In this scenario it is challenging to adapt systems to a specific target domain. To address this problem we consider the recently released OpenAI Whisper ASR as an example of a large-scale ASR system to assess adaptation methods. An error correction based approach is adopted, as this does not require access to the model, but can be trained from either 1-best or N-best outputs that are normally available via the ASR API. LibriSpeech is used as the primary target domain for adaptation. The generalization ability of the system in two distinct dimensions are then evaluated. First, whether the form of correction model is portable to other speech recognition domains, and secondly whether it can be used for ASR models having a different architecture.

Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin et al.

ASR systems are generally built for the spoken 'standard', and their performance declines for non-standard dialects/varieties. This is a problem for a language like Irish, where there is no single spoken standard, but rather three major dialects: Ulster (Ul), Connacht (Co) and Munster (Mu). As a diagnostic to quantify the effect of the speaker's dialect on recognition performance, 12 ASR systems were trained, firstly using baseline dialect-balanced training corpora, and then using modified versions of the baseline corpora, where dialect-specific materials were either subtracted or added. Results indicate that dialect-balanced corpora do not yield a similar performance across the dialects: the Ul dialect consistently underperforms, whereas Mu yields lowest WERs. There is a close relationship between Co and Mu dialects, but one that is not symmetrical. These results will guide future corpus collection and system building strategies to optimise for cross-dialect performance equity.

Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin et al.

The Irish language is rich in its diversity of dialects and accents. This compounds the difficulty of creating a speech recognition system for the low-resource language, as such a system must contend with a high degree of variability with limited corpora. A recent study investigating dialect bias in Irish ASR found that balanced training corpora gave rise to unequal dialect performance, with performance for the Ulster dialect being consistently worse than for the Connacht or Munster dialects. Motivated by this, the present experiments investigate spoken dialect identification of Irish, with a view to incorporating such a system into the speech recognition pipeline. Two acoustic classification models are tested, XLS-R and ECAPA-TDNN, in conjunction with a text-based classifier using a pretrained Irish-language BERT model. The ECAPA-TDNN, particularly a model pretrained for language identification on the VoxLingua107 dataset, performed best overall, with an accuracy of 73%. This was further improved to 76% by fusing the model's outputs with the text-based model. The Ulster dialect was most accurately identified, with an accuracy of 94%, however the model struggled to disambiguate between the Connacht and Munster dialects, suggesting a more nuanced approach may be necessary to robustly distinguish between the dialects of Irish.

Rao Ma, Mengjie Qian, Yassir Fathullah et al.

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation model with strong performance on speech recognition and English translation, is used as the example model. Using speech-to-speech retrieval to analyse the audio representations generated by the encoder, we show that utterances from different languages are mapped to a shared semantic space. This shared embedding space can then be leveraged for zero-shot cross-lingual transfer in speech translation. By fine-tuning the Whisper decoder with only English-to-Chinese speech translation data, improved performance for translation to Chinese can be obtained for multiple languages, in addition to English. Furthermore, for languages related to those seen in training it is possible to perform speech translation, despite the model never seeing the language in training, or being able to perform transcription.

Rao Ma, Mengjie Qian, Mark Gales et al.

Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC can improve performance and provide domain adaptation for black-box ASR systems. This work investigates the use of large language models (LLMs) for error correction across diverse scenarios. 1-best ASR hypotheses are commonly used as the input to EC models. We propose building high-performance EC models using ASR N-best lists which should provide more contextual information for the correction process. Additionally, the generation process of a standard EC model is unrestricted in the sense that any output sequence can be generated. For some scenarios, such as unseen domains, this flexibility may impact performance. To address this, we introduce a constrained decoding approach based on the N-best list or an ASR lattice. Finally, most EC models are trained for a specific ASR system requiring retraining whenever the underlying ASR system is changed. This paper explores the ability of EC models to operate on the output of different ASR systems. This concept is further extended to zero-shot error correction using LLMs, such as ChatGPT. Experiments on three standard datasets demonstrate the efficacy of our proposed methods for both Transducer and attention-based encoder-decoder ASR systems. In addition, the proposed method can serve as an effective method for model ensembling.

Stefano Bannò, Rao Ma, Mengjie Qian et al.

Natural language-based assessment (NLA) is an approach to second language assessment that uses instructions - expressed in the form of can-do descriptors - originally intended for human examiners, aiming to determine whether large language models (LLMs) can interpret and apply them in ways comparable to human assessment. In this work, we explore the use of such descriptors with an open-source LLM, Qwen 2.5 72B, to assess responses from the publicly available S&I Corpus in a zero-shot setting. Our results show that this approach - relying solely on textual information - achieves competitive performance: while it does not outperform state-of-the-art speech LLMs fine-tuned for the task, it surpasses a BERT-based model trained specifically for this purpose. NLA proves particularly effective in mismatched task settings, is generalisable to other data types and languages, and offers greater interpretability, as it is grounded in clearly explainable, widely applicable language descriptors.

Mengjie Qian, Guangzhi Sun, Mark J. F. Gales et al.

Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements. Existing approaches typically rely on single judges or aggregate multiple judges assuming equal reliability. In practice, LLM judges vary substantially in performance across tasks and aspects, and their judgment probabilities may be biased and inconsistent. Furthermore, human-labelled supervision for judge calibration may be unavailable. We first empirically demonstrate that inconsistencies in LLM comparison probabilities exist and show that it limits the effectiveness of direct probability-based ranking. To address this, we study the LLM-as-a-jury setting and propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone. Experiments on benchmark NLG evaluation datasets show that BT-sigma consistently outperforms averaging-based aggregation methods, and that the learned discriminator strongly correlates with independent measures of the cycle consistency of LLM judgments. Further analysis reveals that BT-sigma can be interpreted as an unsupervised calibration mechanism that improves aggregation by modelling judge reliability.

Kate Knill, Diane Nicholls, Mark J. F. Gales et al.

We introduce the Speak & Improve Corpus 2025, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform. The aim of the corpus release is to address a major challenge to developing L2 spoken language processing systems, the lack of publicly available data with high-quality annotations. It is being made available for non-commercial use on the ELiT website. In designing this corpus we have sought to make it cover a wide-range of speaker attributes, from their L1 to their speaking ability, as well as providing manual annotations. This enables a range of language-learning tasks to be examined, such as assessing speaking proficiency or providing feedback on grammatical errors in a learner's speech. Additionally the data supports research into the underlying technology required for these tasks including automatic speech recognition (ASR) of low resource L2 learner English, disfluency detection or spoken grammatical error correction (GEC). The corpus consists of around 315 hours of L2 English learners audio with holistic scores, and a subset of audio annotated with transcriptions and error labels.

Mengjie Qian, Kate Knill, Stefano Banno et al.

This paper presents the "Speak & Improve Challenge 2025: Spoken Language Assessment and Feedback" -- a challenge associated with the ISCA SLaTE 2025 Workshop. The goal of the challenge is to advance research on spoken language assessment and feedback, with tasks associated with both the underlying technology and language learning feedback. Linked with the challenge, the Speak & Improve (S&I) Corpus 2025 is being pre-released, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform. The corpus consists of approximately 315 hours of audio data from second language English learners with holistic scores, and a 55-hour subset with manual transcriptions and error labels. The Challenge has four shared tasks: Automatic Speech Recognition (ASR), Spoken Language Assessment (SLA), Spoken Grammatical Error Correction (SGEC), and Spoken Grammatical Error Correction Feedback (SGECF). Each of these tasks has a closed track where a predetermined set of models and data sources are allowed to be used, and an open track where any public resource may be used. Challenge participants may do one or more of the tasks. This paper describes the challenge, the S&I Corpus 2025, and the baseline systems released for the Challenge.

Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin et al.

This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the current best performing models trained for ASR (TDNN-HMM) and DID (ECAPA-TDNN). An optimal InterCTC setting is initially established using a Conformer encoder. This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared. A multi-task fine-tuning approach is adopted for language model (LM) shallow fusion. The experiments yielded an improvement in DID accuracy of 10.8% relative to a baseline ECAPA-TDNN, and WER performance approaching the TDNN-HMM model. This multi-task approach emerges as a promising strategy for Irish low-resource ASR and DID.

Rao Ma, Mengjie Qian, Siyuan Tang et al.

The growing population of L2 English speakers has increased the demand for developing automatic graders for spoken language assessment (SLA). Historically, statistical models, text encoders, and self-supervised speech models have been utilised for this task. However, cascaded systems suffer from the loss of information, while E2E graders also have limitations. With the recent advancements of multi-modal large language models (LLMs), we aim to explore their potential as L2 oral proficiency graders and overcome these issues. In this work, we compare various training strategies using regression and classification targets. Our results show that speech LLMs outperform all previous competitive baselines, achieving superior performance on two datasets. Furthermore, the trained grader demonstrates strong generalisation capabilities in the cross-part or cross-task evaluation, facilitated by the audio understanding knowledge acquired during LLM pre-training.

Mengjie Qian, Rao Ma, Stefano Bannò et al.

Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and removal and one for GEC. With the rise of end-to-end (E2E) speech foundation models, we investigate their effectiveness in SGEC and feedback generation. This work introduces a pseudo-labelling process to address the challenge of limited labelled data, expanding the training data size from 77 hours to approximately 2500 hours, leading to improved performance. Additionally, we prompt an E2E Whisper-based SGEC model with fluent transcriptions, showing a slight improvement in SGEC performance, with more significant gains in feedback generation. Finally, we assess the impact of increasing model size, revealing that while pseudo-labelled data does not yield performance gain for a larger Whisper model, training with prompts proves beneficial.

Penny Karanasou, Mengjie Qian, Stefano Bannò et al.

While there exist strong benchmark datasets for grammatical error correction (GEC), high-quality annotated spoken datasets for Spoken GEC (SGEC) are still under-resourced. In this paper, we propose a fully automated method to generate audio-text pairs with grammatical errors and disfluencies. Moreover, we propose a series of objective metrics that can be used to evaluate the generated data and choose the more suitable dataset for SGEC. The goal is to generate an augmented dataset that maintains the textual and acoustic characteristics of the original data while providing new types of errors. This augmented dataset should augment and enrich the original corpus without altering the language assessment scores of the second language (L2) learners. We evaluate the use of the augmented corpus both for written GEC (the text part) and for SGEC (the audio-text pairs). Our experiments are conducted on the S\&I Corpus, the first publicly available speech dataset with grammar error annotations.

Mengjie Qian, Rao Ma, Stefano Bannò et al.

Grammatical Error Correction (GEC) and feedback play a vital role in supporting second language (L2) learners, educators, and examiners. While written GEC is well-established, spoken GEC (SGEC), aiming to provide feedback based on learners' speech, poses additional challenges due to disfluencies, transcription errors, and the lack of structured input. SGEC systems typically follow a cascaded pipeline consisting of Automatic Speech Recognition (ASR), disfluency detection, and GEC, making them vulnerable to error propagation across modules. This work examines an End-to-End (E2E) framework for SGEC and feedback generation, highlighting challenges and possible solutions when developing these systems. Cascaded, partial-cascaded and E2E architectures are compared, all built on the Whisper foundation model. A challenge for E2E systems is the scarcity of GEC labeled spoken data. To address this, an automatic pseudo-labeling framework is examined, increasing the training data from 77 to over 2500 hours. To improve the accuracy of the SGEC system, additional contextual information, exploiting the ASR output, is investigated. Candidate feedback of their mistakes is an essential step to improving performance. In E2E systems the SGEC output must be compared with an estimate of the fluent transcription to obtain the feedback. To improve the precision of this feedback, a novel reference alignment process is proposed that aims to remove hypothesised edits that results from fluent transcription errors. Finally, these approaches are combined with an edit confidence estimation approach, to exclude low-confidence edits. Experiments on the in-house Linguaskill (LNG) corpora and the publicly available Speak & Improve (S&I) corpus show that the proposed approaches significantly boost E2E SGEC performance.

Liam Lonergan, Ibon Saratxaga, John Sloan et al.

This paper sets out the first web-based transcription system for the Irish language - Fotheidil, a system that utilises speech-related AI technologies as part of the ABAIR initiative. The system includes both off-the-shelf pre-trained voice activity detection and speaker diarisation models and models trained specifically for Irish automatic speech recognition and capitalisation and punctuation restoration. Semi-supervised learning is explored to improve the acoustic model of a modular TDNN-HMM ASR system, yielding substantial improvements for out-of-domain test sets and dialects that are underrepresented in the supervised training set. A novel approach to capitalisation and punctuation restoration involving sequence-to-sequence models is compared with the conventional approach using a classification model. Experimental results show here also substantial improvements in performance. The system will be made freely available for public use, and represents an important resource to researchers and others who transcribe Irish language materials. Human-corrected transcriptions will be collected and included in the training dataset as the system is used, which should lead to incremental improvements to the ASR model in a cyclical, community-driven fashion.

Rao Ma, Mengjie Qian, Vyas Raina et al.

The combination of pre-trained speech encoders with large language models has enabled the development of speech LLMs that can handle a wide range of spoken language processing tasks. While these models are powerful and flexible, this very flexibility may make them more vulnerable to adversarial attacks. To examine the extent of this problem, in this work we investigate universal acoustic adversarial attacks on speech LLMs. Here a fixed, universal, adversarial audio segment is prepended to the original input audio. We initially investigate attacks that cause the model to either produce no output or to perform a modified task overriding the original prompt. We then extend the nature of the attack to be selective so that it activates only when specific input attributes, such as a speaker gender or spoken language, are present. Inputs without the targeted attribute should be unaffected, allowing fine-grained control over the model outputs. Our findings reveal critical vulnerabilities in Qwen2-Audio and Granite-Speech and suggest that similar speech LLMs may be susceptible to universal adversarial attacks. This highlights the need for more robust training strategies and improved resistance to adversarial attacks.

Erfan Loweimi, Mengjie Qian, Kate Knill et al. · cambridge

There is a growing abundance of publicly available or company-owned audio/video archives, highlighting the increasing importance of efficient access to desired content and information retrieval from these archives. This paper investigates the challenges, solutions, effectiveness, and robustness of speaker retrieval systems developed "in the wild" which involves addressing two primary challenges: extraction of task-relevant labels from limited metadata for system development and evaluation, as well as the unconstrained acoustic conditions encountered in the archive, ranging from quiet studios to adverse noisy environments. While we focus on the publicly-available BBC Rewind archive (spanning 1948 to 1979), our framework addresses the broader issue of speaker retrieval on extensive and possibly aged archives with no control over the content and acoustic conditions. Typically, these archives offer a brief and general file description, mostly inadequate for specific applications like speaker retrieval, and manual annotation of such large-scale archives is unfeasible. We explore various aspects of system development (e.g., speaker diarisation, embedding extraction, query selection) and analyse the challenges, possible solutions, and their functionality. To evaluate the performance, we conduct systematic experiments in both clean setup and against various distortions simulating real-world applications. Our findings demonstrate the effectiveness and robustness of the developed speaker retrieval systems, establishing the versatility and scalability of the proposed framework for a wide range of applications beyond the BBC Rewind corpus.