Ahmed Ali

Fahim Dalvi, Maram Hasanain, Sabri Boughorbel et al.

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online. (https://youtu.be/9cC2m_abk3A)

Sanjay Chawla, Preslav Nakov, Ahmed Ali et al. · berkeley

It is ten years since neural networks made their spectacular comeback. Prompted by this anniversary, we take a holistic perspective on Artificial Intelligence (AI). Supervised Learning for cognitive tasks is effectively solved - provided we have enough high-quality labeled data. However, deep neural network models are not easily interpretable, and thus the debate between blackbox and whitebox modeling has come to the fore. The rise of attention networks, self-supervised learning, generative modeling, and graph neural networks has widened the application space of AI. Deep Learning has also propelled the return of reinforcement learning as a core building block of autonomous decision making systems. The possible harms made possible by new AI technologies have raised socio-technical issues such as transparency, fairness, and accountability. The dominance of AI by Big-Tech who control talent, computing resources, and most importantly, data may lead to an extreme AI divide. Failure to meet high expectations in high profile, and much heralded flagship projects like self-driving vehicles could trigger another AI winter.

Massa Baali, Tomoki Hayashi, Hamdy Mubarak et al.

Several high-resource Text to Speech (TTS) systems currently produce natural, well-established human-like speech. In contrast, low-resource languages, including Arabic, have very limited TTS systems due to the lack of resources. We propose a fully unsupervised method for building TTS, including automatic data selection and pre-training/fine-tuning strategies for TTS training, using broadcast news as a case study. We show how careful selection of data, yet smaller amounts, can improve the efficiency of TTS system in generating more natural speech than a system trained on a bigger dataset. We adopt to propose different approaches for the: 1) data: we applied automatic annotations using DNSMOS, automatic vowelization, and automatic speech recognition (ASR) for fixing transcriptions' errors; 2) model: we used transfer learning from high-resource language in TTS model and fine-tuned it with one hour broadcast recording then we used this model to guide a FastSpeech2-based Conformer model for duration. Our objective evaluation shows 3.9% character error rate (CER), while the groundtruth has 1.3% CER. As for the subjective evaluation, where 1 is bad and 5 is excellent, our FastSpeech2-based Conformer model achieved a mean opinion score (MOS) of 4.4 for intelligibility and 4.2 for naturalness, where many annotators recognized the voice of the broadcaster, which proves the effectiveness of our proposed unsupervised method.

Amir Hussein, Dorsa Zeinali, Ondřej Klejch et al.

Designing effective automatic speech recognition (ASR) systems for Code-Switching (CS) often depends on the availability of the transcribed CS resources. To address data scarcity, this paper introduces Speech Collage, a method that synthesizes CS data from monolingual corpora by splicing audio segments. We further improve the smoothness quality of audio generation using an overlap-add approach. We investigate the impact of generated data on speech recognition in two scenarios: using in-domain CS text and a zero-shot approach with synthesized CS text. Empirical results highlight up to 34.4% and 16.2% relative reductions in Mixed-Error Rate and Word-Error Rate for in-domain and zero-shot scenarios, respectively. Lastly, we demonstrate that CS augmentation bolsters the model's code-switching inclination and reduces its monolingual bias.

Injy Hamed, Amir Hussein, Oumnia Chellah et al.

Code-switching poses a number of challenges and opportunities for multilingual automatic speech recognition. In this paper, we focus on the question of robust and fair evaluation metrics. To that end, we develop a reference benchmark data set of code-switching speech recognition hypotheses with human judgments. We define clear guidelines for minimal editing of automatic hypotheses. We validate the guidelines using 4-way inter-annotator agreement. We evaluate a large number of metrics in terms of correlation with human judgments. The metrics we consider vary in terms of representation (orthographic, phonological, semantic), directness (intrinsic vs extrinsic), granularity (e.g. word, character), and similarity computation method. The highest correlation to human judgment is achieved using transliteration followed by text normalization. We release the first corpus for human acceptance of code-switching speech recognition results in dialectal Arabic/English conversation speech.

Shammur Absar Chowdhury, Ahmed Ali

The success of the multilingual automatic speech recognition systems empowered many voice-driven applications. However, measuring the performance of such systems remains a major challenge, due to its dependency on manually transcribed speech data in both mono- and multilingual scenarios. In this paper, we propose a novel multilingual framework -- eWER3 -- jointly trained on acoustic and lexical representation to estimate word error rate. We demonstrate the effectiveness of eWER3 to (i) predict WER without using any internal states from the ASR and (ii) use the multilingual shared latent space to push the performance of the close-related languages. We show our proposed multilingual model outperforms the previous monolingual word error rate estimation method (eWER2) by an absolute 9\% increase in Pearson correlation coefficient (PCC), with better overall estimation between the predicted and reference WER.

Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali et al.

The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to overcome such data scarcity. The SpeechBlender utilizes varieties of masks to target different regions of phonetic units, and use the mixing factors to linearly interpolate raw speech signals while augmenting pronunciation. The masks facilitate smooth blending of the signals, generating more effective samples than the `Cut/Paste' method. Our proposed technique achieves state-of-the-art results, with Speechocean762, on ASR dependent mispronunciation detection models at phoneme level, with a 2.0% gain in Pearson Correlation Coefficient (PCC) compared to the previous state-of-the-art [1]. Additionally, we demonstrate a 5.0% improvement at the phoneme level compared to our baseline. We also observed a 4.6% increase in F1-score with Arabic AraVoiceL2 testset.

Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali

The phonological discrepancies between a speaker's native (L1) and the non-native language (L2) serves as a major factor for mispronunciation. This paper introduces a novel multilingual MDD architecture, L1-MultiMDD, enriched with L1-aware speech representation. An end-to-end speech encoder is trained on the input signal and its corresponding reference phoneme sequence. First, an attention mechanism is deployed to align the input audio with the reference phoneme sequence. Afterwards, the L1-L2-speech embedding are extracted from an auxiliary model, pretrained in a multi-task setup identifying L1 and L2 language, and are infused with the primary network. Finally, the L1-MultiMDD is then optimized for a unified multilingual phoneme recognition task using connectionist temporal classification (CTC) loss for the target languages: English, Arabic, and Mandarin. Our experiments demonstrate the effectiveness of the proposed L1-MultiMDD framework on both seen -- L2-ARTIC, LATIC, and AraVoiceL2v2; and unseen -- EpaDB and Speechocean762 datasets. The consistent gains in PER, and false rejection rate (FRR) across all target languages confirm our approach's robustness, efficacy, and generalizability.

Massa Baali, Wassim El-Hajj, Ahmed Ali

Dubbed series are gaining a lot of popularity in recent years with strong support from major media service providers. Such popularity is fueled by studies that showed that dubbed versions of TV shows are more popular than their subtitled equivalents. We propose an unsupervised approach to construct speech-to-speech corpus, aligned on short segment levels, to produce a parallel speech corpus in the source- and target- languages. Our methodology exploits video frames, speech recognition, machine translation, and noisy frames removal algorithms to match segments in both languages. To verify the performance of the proposed method, we apply it on long and short dubbed clips. Out of 36 hours TR-AR dubbed series, our pipeline was able to generate 17 hours of paired segments, which is about 47% of the corpus. We applied our method on another language pair, EN-AR, to ensure it is robust enough and not tuned for a specific language or a specific corpus. Regardless of the language pairs, the accuracy of the paired segments was around 70% when evaluated using human subjective evaluation. The corpus will be freely available for the research community.

Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali

Research on pronunciation assessment systems focuses on utilizing phonetic and phonological aspects of non-native (L2) speech, often neglecting the rich layer of information hidden within the non-verbal cues. In this study, we proposed a novel pronunciation assessment framework, IntraVerbalPA. % The framework innovatively incorporates both fine-grained frame- and abstract utterance-level non-verbal cues, alongside the conventional speech and phoneme representations. Additionally, we introduce ''Goodness of phonemic-duration'' metric to effectively model duration distribution within the framework. Our results validate the effectiveness of the proposed IntraVerbalPA framework and its individual components, yielding performance that either matches or outperforms existing research works.

Yassine El Kheir, Ahmed Ali, Shammur Absar Chowdhury

Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years. With the rapid growth in language processing and deep learning over the past few years, there is a need for an updated review. In this paper, we review methods employed in pronunciation assessment for both phonemic and prosodic. We categorize the main challenges observed in prominent research trends, and highlight existing limitations, and available resources. This is followed by a discussion of the remaining challenges and possible directions for future work.

Yousseif Elshahawy, Yassine El Kheir, Shammur Absar Chowdhury et al.

We introduce MyVoice, a crowdsourcing platform designed to collect Arabic speech to enhance dialectal speech technologies. This platform offers an opportunity to design large dialectal speech datasets; and makes them publicly available. MyVoice allows contributors to select city/country-level fine-grained dialect and record the displayed utterances. Users can switch roles between contributors and annotators. The platform incorporates a quality assurance system that filters out low-quality and spurious recordings before sending them for validation. During the validation phase, contributors can assess the quality of recordings, annotate them, and provide feedback which is then reviewed by administrators. Furthermore, the platform offers flexibility to admin roles to add new data or tasks beyond dialectal speech and word collection, which are displayed to contributors. Thus, enabling collaborative efforts in gathering diverse and large Arabic speech data.

Massa Baali, Ahmed Ali

This paper presents FOOCTTS, an automatic pipeline for a football commentator that generates speech with background crowd noise. The application gets the text from the user, applies text pre-processing such as vowelization, followed by the commentator's speech synthesizer. Our pipeline included Arabic automatic speech recognition for data labeling, CTC segmentation, transcription vowelization to match speech, and fine-tuning the TTS. Our system is capable of generating speech with its acoustic environment within limited 15 minutes of football commentator recording. Our prototype is generalizable and can be easily applied to different domains and languages.

Yassine El Kheir, Amit Meghanani, Mostafa Shahin et al.

We present the findings of the second edition of the IQRA Interspeech Challenge, a challenge on automatic Mispronunciation Detection and Diagnosis (MDD) for Modern Standard Arabic (MSA). Building on the previous edition, this iteration introduces \textbf{Iqra\_Extra\_IS26}, a new dataset of authentic human mispronounced speech, complementing the existing training and evaluation resources. Submitted systems employed a diverse range of approaches, spanning CTC-based self-supervised learning models, two-stage fine-tuning strategies, and using large audio-language models. Compared to the first edition, we observe a substantial jump of \textbf{0.28 in F1-score}, attributable both to novel architectures and modeling strategies proposed by participants and to the additional authentic mispronunciation data made available. These results demonstrate the growing maturity of Arabic MDD research and establish a stronger foundation for future work in Arabic pronunciation assessment.

Brian Yan, Injy Hamed, Shuichiro Shimizu et al. · cmu

We present CS-FLEURS, a new dataset for developing and evaluating code-switched speech recognition and translation systems beyond high-resourced languages. CS-FLEURS consists of 4 test sets which cover in total 113 unique code-switched language pairs across 52 languages: 1) a 14 X-English language pair set with real voices reading synthetically generated code-switched sentences, 2) a 16 X-English language pair set with generative text-to-speech 3) a 60 {Arabic, Mandarin, Hindi, Spanish}-X language pair set with the generative text-to-speech, and 4) a 45 X-English lower-resourced language pair test set with concatenative text-to-speech. Besides the four test sets, CS-FLEURS also provides a training set with 128 hours of generative text-to-speech data across 16 X-English language pairs. Our hope is that CS-FLEURS helps to broaden the scope of future code-switched speech research. Dataset link: https://huggingface.co/datasets/byan/cs-fleurs.

Ali Alhejab, Tomas Zelezny, Lamya Alkanhal et al.

This paper explores the application of T5 models for Saudi Sign Language (SSL) translation using a novel dataset. The SSL dataset includes three challenging testing protocols, enabling comprehensive evaluation across different scenarios. Additionally, it captures unique SSL characteristics, such as face coverings, which pose challenges for sign recognition and translation. In our experiments, we investigate the impact of pre-training on American Sign Language (ASL) data by comparing T5 models pre-trained on the YouTubeASL dataset with models trained directly on the SSL dataset. Experimental results demonstrate that pre-training on YouTubeASL significantly improves models' performance (roughly $3\times$ in BLEU-4), indicating cross-linguistic transferability in sign language models. Our findings highlight the benefits of leveraging large-scale ASL data to improve SSL translation and provide insights into the development of more effective sign language translation systems. Our code is publicly available at our GitHub repository.

Ahmed Ali, Chiara Gabellieri, Antonio Franchi

In this paper, we describe procedures for computing higher-order time derivatives of the Lie-group Newton-Euler, Articulated-Body Inertia, and hybrid dynamics algorithms for floating-base trees, where the base configuration evolves on SE(3) and the attached mechanism is an open kinematic tree with configuration on the (n1+n2)-dimensional manifold T^{n1} \times R^{n2}, using spatial representation of twists. After presenting the algorithms, we collect the resulting recursions into closed-form equations of motion, identifying an admissible Coriolis matrix satisfying the passivity property, and showing that the articulated inertia tensor remains unchanged across all time derivatives. We then apply the developed methods to a 12-DoF aerial manipulator to derive analytical expressions for its geometric forward and inverse dynamics along with their first time derivatives whereas the numerical simulations successfully evaluate these dynamics up to fifth order. Finally, to demonstrate their practical utility, we benchmark the proposed extensions and show that, in the considered tests, their computational cost scales quadratically with the derivative order, whereas the automatic-differentiation baseline exhibits exponential scaling.

Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad et al.

We present Fanar, a platform for Arabic-centric multimodal generative AI systems, that supports language, speech and image generation tasks. At the heart of Fanar are Fanar Star and Fanar Prime, two highly capable Arabic Large Language Models (LLMs) that are best in the class on well established benchmarks for similar sized models. Fanar Star is a 7B (billion) parameter model that was trained from scratch on nearly 1 trillion clean and deduplicated Arabic, English and Code tokens. Fanar Prime is a 9B parameter model continually trained on the Gemma-2 9B base model on the same 1 trillion token set. Both models are concurrently deployed and designed to address different types of prompts transparently routed through a custom-built orchestrator. The Fanar platform provides many other capabilities including a customized Islamic Retrieval Augmented Generation (RAG) system for handling religious prompts, a Recency RAG for summarizing information about current or recent events that have occurred after the pre-training data cut-off date. The platform provides additional cognitive capabilities including in-house bilingual speech recognition that supports multiple Arabic dialects, voice and image generation that is fine-tuned to better reflect regional characteristics. Finally, Fanar provides an attribution service that can be used to verify the authenticity of fact based generated content. The design, development, and implementation of Fanar was entirely undertaken at Hamad Bin Khalifa University's Qatar Computing Research Institute (QCRI) and was sponsored by Qatar's Ministry of Communications and Information Technology to enable sovereign AI technology development.

Mahmoud Bekhit, Ahmad Salah, Ahmed Salim Alrawahi et al.

Motion capture (MoCap) data from wearable Inertial Measurement Units (IMUs) is vital for applications in sports science, but its utility is often compromised by missing data. Despite numerous imputation techniques, a systematic performance evaluation for IMU-derived MoCap time-series data is lacking. We address this gap by conducting a comprehensive comparative analysis of statistical, machine learning, and deep learning imputation methods. Our evaluation considers three distinct contexts: univariate time-series, multivariate across subjects, and multivariate across kinematic angles. To facilitate this benchmark, we introduce the first publicly available MoCap dataset designed specifically for imputation, featuring data from 53 karate practitioners. We simulate three controlled missingness mechanisms: missing completely at random (MCAR), block missingness, and a novel value-dependent pattern at signal transition points. Our experiments, conducted on 39 kinematic variables across all subjects, reveal that multivariate imputation frameworks consistently outperform univariate approaches, particularly for complex missingness. For instance, multivariate methods achieve up to a 50% mean absolute error reduction (MAE from 10.8 to 5.8) compared to univariate techniques for transition point missingness. Advanced models like Generative Adversarial Imputation Networks (GAIN) and Iterative Imputers demonstrate the highest accuracy in these challenging scenarios. This work provides a critical baseline for future research and offers practical recommendations for improving the integrity and robustness of Mo-Cap data analysis.

Ahmed Abdelali, Hamdy Mubarak, Shammur Absar Chowdhury et al.

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particular languages and tasks. LAraBench addresses this gap for Arabic Natural Language Processing (NLP) and Speech Processing tasks, including sequence tagging and content classification across different domains. We utilized models such as GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM, employing zero and few-shot learning techniques to tackle 33 distinct tasks across 61 publicly available datasets. This involved 98 experimental setups, encompassing ~296K data points, ~46 hours of speech, and 30 sentences for Text-to-Speech (TTS). This effort resulted in 330+ sets of experiments. Our analysis focused on measuring the performance gap between SOTA models and LLMs. The overarching trend observed was that SOTA models generally outperformed LLMs in zero-shot learning, with a few exceptions. Notably, larger computational models with few-shot learning techniques managed to reduce these performance gaps. Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.

Yassine El Kheir, Fouad Khnaisser, Shammur Absar Chowdhury et al.

This paper introduces a novel Arabic pronunciation learning application QVoice, powered with end-to-end mispronunciation detection and feedback generator module. The application is designed to support non-native Arabic speakers in enhancing their pronunciation skills, while also helping native speakers mitigate any potential influence from regional dialects on their Modern Standard Arabic (MSA) pronunciation. QVoice employs various learning cues to aid learners in comprehending meaning, drawing connections with their existing knowledge of English language, and offers detailed feedback for pronunciation correction, along with contextual examples showcasing word usage. The learning cues featured in QVoice encompass a wide range of meaningful information, such as visualizations of phrases/words and their translations, as well as phonetic transcriptions and transliterations. QVoice provides pronunciation feedback at the character level and assesses performance at the word level.

Michael Aupetit, Ahmed Ali

In multiclass classification of multidimensional data, the user wants to build a model of the classes to predict the label of unseen data. The model is trained on the data and tested on unseen data with known labels to evaluate its quality. The results are visualized as a confusion matrix which shows how many data labels have been predicted correctly or confused with other classes. The multidimensional nature of the data prevents the direct visualization of the classes so we design ClassSPLOM to give more perceptual insights about the classification results. It uses the Scatterplot Matrix (SPLOM) metaphor to visualize a Linear Discriminant Analysis projection of the data for each pair of classes and a set of Receiving Operating Curves to evaluate their trustworthiness. We illustrate ClassSPLOM on a use case in Arabic dialects identification.

Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali et al.

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical structure complexity, and domain mismatch. The most common method for addressing CS is to train an ASR system with the available transcribed CS speech, along with monolingual data. In this work, we propose a zero-shot learning methodology for CS-ASR by augmenting the monolingual data with artificially generating CS text. We based our approach on random lexical replacements and Equivalence Constraint (EC) while exploiting aligned translation pairs to generate random and grammatically valid CS content. Our empirical results show a 65.5% relative reduction in language model perplexity, and 7.7% in ASR WER on two ecologically valid CS test sets. The human evaluation of the generated text using EC suggests that more than 80% is of adequate quality.

Ahmed Ali, Shammur Chowdhury, Amir Hussein et al.

Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual modeling for ASR through a series of large-scale ASR experiments. Our innovative framework deploys a multi-graph approach in the weighted finite state transducers (WFST) framework. We compare our WFST decoding strategies with a transformer sequence to sequence system trained on the same data. Given a code-switching scenario between Arabic and English languages, our results show that the WFST decoding approaches were more suitable for the intersentential code-switching datasets. In addition, the transformer system performed better for intrasentential code-switching task. With this study, we release an artificially generated development and test sets, along with ecological code-switching test set, to benchmark the ASR performance.

Shammur Absar Chowdhury, Nadir Durrani, Ahmed Ali

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not only for debugging purposes but also for ensuring fairness in ethical decision-making. In our study, we conduct a post-hoc functional interpretability analysis of pretrained speech models using the probing framework [1]. Specifically, we analyze utterance-level representations of speech models trained for various tasks such as speaker recognition and dialect identification. We conduct layer and neuron-wise analyses, probing for speaker, language, and channel properties. Our study aims to answer the following questions: i) what information is captured within the representations? ii) how is it represented and distributed? and iii) can we identify a minimal subset of the network that possesses this information? Our results reveal several novel findings, including: i) channel and gender information are distributed across the network, ii) the information is redundantly available in neurons with respect to a task, iii) complex properties such as dialectal information are encoded only in the task-oriented pretrained network, iv) and is localised in the upper layers, v) we can extract a minimal subset of neurons encoding the pre-defined property, vi) salient neurons are sometimes shared between properties, vii) our analysis highlights the presence of biases (for example gender) in the network. Our cross-architectural comparison indicates that: i) the pretrained models capture speaker-invariant information, and ii) CNN models are competitive with Transformer models in encoding various understudied properties.

Hamdy Mubarak, Amir Hussein, Shammur Absar Chowdhury et al.

We introduce the largest transcribed Arabic speech corpus, QASR, collected from the broadcast domain. This multi-dialect speech dataset contains 2,000 hours of speech sampled at 16kHz crawled from Aljazeera news channel. The dataset is released with lightly supervised transcriptions, aligned with the audio segments. Unlike previous datasets, QASR contains linguistically motivated segmentation, punctuation, speaker information among others. QASR is suitable for training and evaluating speech recognition systems, acoustics- and/or linguistics- based Arabic dialect identification, punctuation restoration, speaker identification, speaker linking, and potentially other NLP modules for spoken data. In addition to QASR transcription, we release a dataset of 130M words to aid in designing and training a better language model. We show that end-to-end automatic speech recognition trained on QASR reports a competitive word error rate compared to the previous MGB-2 corpus. We report baseline results for downstream natural language processing tasks such as named entity recognition using speech transcript. We also report the first baseline for Arabic punctuation restoration. We make the corpus available for the research community.

Amir Hussein, Shammur Chowdhury, Najim Dehak et al.

The success in designing Code-Switching (CS) ASR often depends on the availability of the transcribed CS resources. Such dependency harms the development of ASR in low-resourced languages such as Bengali and Hindi. In this paper, we exploit the transfer learning approach to design End-to-End (E2E) CS ASR systems for the two low-resourced language pairs using different monolingual speech data and a small set of noisy CS data. We trained the CS-ASR, following two steps: (i) building a robust bilingual ASR system using a convolution-augmented transformer (Conformer) based acoustic model and n-gram language model, and (ii) fine-tuned the entire E2E ASR with limited noisy CS data. We tested our method on MUCS 2021 challenge and achieved 3rd place in the CS track. We then tested the proposed method using noisy CS data released for Hindi-English and Bengali-English pairs in Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages (MUCS 2021) and achieved 3rd place in the CS track. Unlike, the leading two systems that benefited from crawling YouTube and learning transliteration pairs, our proposed transfer learning approach focused on using only the limited CS data with no data-cleaning or data re-segmentation. Our approach achieved 14.1% relative gain in word error rate (WER) in Hindi-English and 27.1% in Bengali-English. We provide detailed guidelines on the steps to finetune the self-attention based model for limited data for ASR. Moreover, we release the code and recipe used in this paper.

Shammur Absar Chowdhury, Amir Hussein, Ahmed Abdelali et al.

With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In this study, we design a large multilingual end-to-end ASR using self-attention based conformer architecture. We trained the system using Arabic (Ar), English (En) and French (Fr) languages. We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptian and Moroccan); (iii) code-switching -- cross-lingual (Ar-En/Fr) and dialectal (MSA-Egyptian dialect) test cases, and compare with current state-of-the-art systems. Furthermore, we investigate the influence of different embedding/character representations including character vs word-piece; shared vs distinct input symbol per language. Our findings demonstrate the strength of such a model by outperforming state-of-the-art monolingual dialectal Arabic and code-switching Arabic ASR.

Amir Hussein, Shinji Watanabe, Ahmed Ali

Recent advances in automatic speech recognition (ASR) have achieved accuracy levels comparable to human transcribers, which led researchers to debate if the machine has reached human performance. Previous work focused on the English language and modular hidden Markov model-deep neural network (HMM-DNN) systems. In this paper, we perform a comprehensive benchmarking for end-to-end transformer ASR, modular HMM-DNN ASR, and human speech recognition (HSR) on the Arabic language and its dialects. For the HSR, we evaluate linguist performance and lay-native speaker performance on a new dataset collected as a part of this study. For ASR the end-to-end work led to 12.5%, 27.5%, 33.8% WER; a new performance milestone for the MGB2, MGB3, and MGB5 challenges respectively. Our results suggest that human performance in the Arabic language is still considerably better than the machine with an absolute WER gap of 3.5% on average.

Ahmed Ali, Yasser Hifny

Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convolutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2% absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.

Ahmed Ali, Steve Renals

Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive. In this paper, we continue our effort in estimating WER using acoustic, lexical and phonotactic features. Our novel approach to estimate the WER uses a multistream end-to-end architecture. We report results for systems using internal speech decoder features (glass-box), systems without speech decoder features (black-box), and for systems without having access to the ASR system (no-box). The no-box system learns joint acoustic-lexical representation from phoneme recognition results along with MFCC acoustic features to estimate WER. Considering WER per sentence, our no-box system achieves 0.56 Pearson correlation with the reference evaluation and 0.24 root mean square error (RMSE) across 1,400 sentences. The estimated overall WER by e-WER2 is 30.9% for a three hours test set, while the WER computed using the reference transcriptions was 28.5%.

Ramy Baly, Georgi Karadzhov, Jisun An et al.

Predicting the political bias and the factuality of reporting of entire news outlets are critical elements of media profiling, which is an understudied but an increasingly important research direction. The present level of proliferation of fake, biased, and propagandistic content online, has made it impossible to fact-check every single suspicious claim, either manually or automatically. Alternatively, we can profile entire news outlets and look for those that are likely to publish fake or biased content. This approach makes it possible to detect likely "fake news" the moment they are published, by simply checking the reliability of their source. From a practical perspective, political bias and factuality of reporting have a linguistic aspect but also a social context. Here, we study the impact of both, namely (i) what was written (i.e., what was published by the target medium, and how it describes itself on Twitter) vs. (ii) who read it (i.e., analyzing the readers of the target medium on Facebook, Twitter, and YouTube). We further study (iii) what was written about the target medium on Wikipedia. The evaluation results show that what was written matters most, and that putting all information sources together yields huge improvements over the current state-of-the-art.

Yoan Dinkov, Ahmed Ali, Ivan Koychev et al.

We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.

Daniel Kopev, Ahmed Ali, Ivan Koychev et al.

We present work on deception detection, where, given a spoken claim, we aim to predict its factuality. While previous work in the speech community has relied on recordings from staged setups where people were asked to tell the truth or to lie and their statements were recorded, here we use real-world political debates. Thanks to the efforts of fact-checking organizations, it is possible to obtain annotations for statements in the context of a political discourse as true, half-true, or false. Starting with such data from the CLEF-2018 CheckThat! Lab, which was limited to text, we performed alignment to the corresponding videos, thus producing a multimodal dataset. We further developed a multimodal deep-learning architecture for the task of deception detection, which yielded sizable improvements over the state of the art for the CLEF-2018 Lab task 2. Our experiments show that the use of the acoustic signal consistently helped to improve the performance compared to using textual and metadata features only, based on several different evaluation measures. We release the new dataset to the research community, hoping to help advance the overall field of multimodal deception detection.

Sameer Khurana, Ahmed Ali, James Glass

We present the speech to text transcription system, called DARTS, for low resource Egyptian Arabic dialect. We analyze the following; transfer learning from high resource broadcast domain to low-resource dialectal domain and semi-supervised learning where we use in-domain unlabeled audio data collected from YouTube. Key features of our system are: A deep neural network acoustic model that consists of a front end Convolutional Neural Network (CNN) followed by several layers of Time Delayed Neural Network (TDNN) and Long-Short Term Memory Recurrent Neural Network (LSTM); sequence discriminative training of the acoustic model; n-gram and recurrent neural network language model for decoding and N-best list rescoring. We show that a simple transfer learning method can achieve good results. The results are further improved by using unlabeled data from YouTube in a semi-supervised setup. Various systems are combined to give the final system that achieves the lowest word error on on the community standard Egyptian-Arabic speech dataset (MGB-3).

Yonatan Belinkov, Ahmed Ali, James Glass

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling, pronunciation lexicon, and language modeling, the end-to-end paradigm is both conceptually simpler and has the potential benefit of training the entire system on the end task. However, such neural network models are more opaque: it is not clear how to interpret the role of different parts of the network and what information it learns during training. In this paper, we analyze the learned internal representations in an end-to-end ASR model. We evaluate the representation quality in terms of several classification tasks, comparing phonemes and graphemes, as well as different articulatory features. We study two languages (English and Arabic) and three datasets, finding remarkable consistency in how different properties are represented in different layers of the deep neural network.

Suwon Shon, Ahmed Ali, James Glass

End-to-end deep learning language or dialect identification systems operate on the spectrogram or other acoustic feature and directly generate identification scores for each class. An important issue for end-to-end systems is to have some knowledge of the application domain, because the system can be vulnerable to use cases that were not seen in the training phase; such a scenario is often referred to as a domain mismatched condition. In general, we assume that there is enough variation in the training dataset to expose the system to multiple domains. In this work, we study how to best make use a training dataset in order to have maximum effectiveness on unknown target domains. Our goal is to process the input without any knowledge of the target domain while preserving robust performance on other domains as well. To accomplish this objective, we propose a domain attentive fusion approach for end-to-end dialect/language identification systems. To help with experimentation, we collect a dataset from three different domains, and create experimental protocols for a domain mismatched condition. The results of our proposed approach, which were tested on a variety of broadcast and YouTube data, shows significant performance gain compared to traditional approaches, even without any prior target domain information.

Suwon Shon, Ahmed Ali, James Glass

Dialect identification (DID) is a special case of general language identification (LID), but a more challenging problem due to the linguistic similarity between dialects. In this paper, we propose an end-to-end DID system and a Siamese neural network to extract language embeddings. We use both acoustic and linguistic features for the DID task on the Arabic dialectal speech dataset: Multi-Genre Broadcast 3 (MGB-3). The end-to-end DID system was trained using three kinds of acoustic features: Mel-Frequency Cepstral Coefficients (MFCCs), log Mel-scale Filter Bank energies (FBANK) and spectrogram energies. We also investigated a dataset augmentation approach to achieve robust performance with limited data resources. Our linguistic feature research focused on learning similarities and dissimilarities between dialects using the Siamese network, so that we can reduce feature dimensionality as well as improve DID performance. The best system using a single feature set achieves 73% accuracy, while a fusion system using multiple features yields 78% on the MGB-3 dialect test set consisting of 5 dialects. The experimental results indicate that FBANK features achieve slightly better results than MFCCs. Dataset augmentation via speed perturbation appears to add significant robustness to the system. Although the Siamese network with language embeddings did not achieve as good a result as the end-to-end DID system, the two approaches had good synergy when combined together in a fused system.

Ahmed Ali, Preslav Nakov, Peter Bell et al.

We study the problem of evaluating automatic speech recognition (ASR) systems that target dialectal speech input. A major challenge in this case is that the orthography of dialects is typically not standardized. From an ASR evaluation perspective, this means that there is no clear gold standard for the expected output, and several possible outputs could be considered correct according to different human annotators, which makes standard word error rate (WER) inadequate as an evaluation metric. Such a situation is typical for machine translation (MT), and thus we borrow ideas from an MT evaluation metric, namely TERp, an extension of translation error rate which is closely-related to WER. In particular, in the process of comparing a hypothesis to a reference, we make use of spelling variants for words and phrases, which we mine from Twitter in an unsupervised fashion. Our experiments with evaluating ASR output for Egyptian Arabic, and further manual analysis, show that the resulting WERd (i.e., WER for dialects) metric, a variant of TERp, is more adequate than WER for evaluating dialectal ASR.

Ahmed Ali, Stephan Vogel, Steve Renals

This paper describes the Arabic MGB-3 Challenge - Arabic Speech Recognition in the Wild. Unlike last year's Arabic MGB-2 Challenge, for which the recognition task was based on more than 1,200 hours broadcast TV news recordings from Aljazeera Arabic TV programs, MGB-3 emphasises dialectal Arabic using a multi-genre collection of Egyptian YouTube videos. Seven genres were used for the data collection: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). A total of 16 hours of videos, split evenly across the different genres, were divided into adaptation, development and evaluation data sets. The Arabic MGB-Challenge comprised two tasks: A) Speech transcription, evaluated on the MGB-3 test set, along with the 10 hour MGB-2 test set to report progress on the MGB-2 evaluation; B) Arabic dialect identification, introduced this year in order to distinguish between four major Arabic dialects - Egyptian, Levantine, North African, Gulf, as well as Modern Standard Arabic. Two hours of audio per dialect were released for development and a further two hours were used for evaluation. For dialect identification, both lexical features and i-vector bottleneck features were shared with participants in addition to the raw audio recordings. Overall, thirteen teams submitted ten systems to the challenge. We outline the approaches adopted in each system, and summarise the evaluation results.

Suwon Shon, Ahmed Ali, James Glass

In order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the 2017 Multi-Genre Broadcast challenge (MGB-3) there were two possible tasks: Arabic speech recognition, and Arabic Dialect Identification (ADI). In this paper, we describe our efforts to create an ADI system for the MGB-3 challenge, with the goal of distinguishing amongst four major Arabic dialects, as well as Modern Standard Arabic. Our research fo- cused on dialect variability and domain mismatches between the training and test domain. In order to achieve a robust ADI system, we explored both Siamese neural network models to learn similarity and dissimilarities among Arabic dialects, as well as i-vector post-processing to adapt domain mismatches. Both Acoustic and linguistic features were used for the final MGB-3 submissions, with the best primary system achieving 75% accuracy on the official 10hr test set.

Sameer Khurana, Ahmed Ali, Steve Renals

In this work, we present a new Vector Space Model (VSM) of speech utterances for the task of spoken dialect identification. Generally, DID systems are built using two sets of features that are extracted from speech utterances; acoustic and phonetic. The acoustic and phonetic features are used to form vector representations of speech utterances in an attempt to encode information about the spoken dialects. The Phonotactic and Acoustic VSMs, thus formed, are used for the task of DID. The aim of this paper is to construct a single VSM that encodes information about spoken dialects from both the Phonotactic and Acoustic VSMs. Given the two views of the data, we make use of a well known multi-view dimensionality reduction technique known as Canonical Correlation Analysis (CCA), to form a single vector representation for each speech utterance that encodes dialect specific discriminative information from both the phonetic and acoustic representations. We refer to this approach as feature space combination approach and show that our CCA based feature vector representation performs better on the Arabic DID task than the phonetic and acoustic feature representations used alone. We also present the feature space combination approach as a viable alternative to the model based combination approach, where two DID systems are built using the two VSMs (Phonotactic and Acoustic) and the final prediction score is the output score combination from the two systems.

Ahmed Ali, Peter Bell, James Glass et al.

This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic speech. Audio data comes from 19 distinct programmes from the Aljazeera Arabic TV channel between March 2005 and December 2015. Programmes are split into three groups: conversations, interviews, and reports. A total of 1,200 hours have been released with lightly supervised transcriptions for the acoustic modelling. For language modelling, we made available over 110M words crawled from Aljazeera Arabic website Aljazeera.net for a 10 year duration 2000-2011. Two lexicons have been provided, one phoneme based and one grapheme based. Finally, two tasks were proposed for this year's challenge: standard speech transcription, and word alignment. This paper describes the task data and evaluation process used in the MGB challenge, and summarises the results obtained.

Ahmed Ali, Najim Dehak, Patrick Cardinal et al.

We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of 100%. We further report results using the proposed method to discriminate between the five most widely used dialects of Arabic: namely Egyptian, Gulf, Levantine, North African, and MSA, with an accuracy of 52%. We discuss dialect identification errors in the context of dialect code-switching between Dialectal Arabic and MSA, and compare the error pattern between manually labeled data, and the output from our classifier. We also release the train and test data as standard corpus for dialect identification.