Non-autoregressive Transformers (NA Ts) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data.

Direct speech-to-speech translation (S2ST), in which all components are trained jointly, is an attractive alternative to cascaded systems because it offers a simpler pipeline and lower inference latency. However, direct S2ST models require large amounts of parallel speech data in the source and target languages, which are rarely available for low-resource languages such as Persian. This paper presents a direct S2ST system for translating Persian speech into English speech, as well as a pipeline for synthetic parallel Persian-English speech generation. The model comprises three components: (1) a conformer-based encoder, initialized from self-supervised pre-training, maps source speech to high-level acoustic representations; (2) a causal transformer decoder with relative position multi-head attention translates these representations into discrete target speech units; (3) a unit-based neural vocoder generates waveforms from the predicted discrete units. To mitigate the data scarcity problem, we construct a new Persian-English parallel speech corpus by translating Persian speech transcriptions into English using a large language model and then synthesizing the corresponding English speech with a state-of-the-art zero-shot text-to-speech system. The resulting corpus increases the amount of available parallel speech by roughly a factor of six. On the Persian-English portion of the CVSS corpus, the proposed model achieves improvement of 4.6 ASR BLEU with the synthetic data over direct baselines. These results indicate that combining self-supervised pre-training, discrete speech units, and synthetic parallel data is effective for improving direct S2ST in low-resource language pairs such as Persian-English

Non-autoregressive Transformers (NA Ts) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data.

This paper investigates discrete unit representations in Speech Language Models (SLMs), focusing on optimizing speech modeling during continual pre-training. In this paper, we systematically examine how model architecture, data representation, and training robustness influence the pre-training stage in which we adapt existing pre-trained language models to the speech modality. Our experiments highlight the role of speech encoders and clustering granularity across different model scales, showing how optimal discretization strategies vary with model capacity. By examining cluster distribution and phonemic alignments, we investigate the effective use of discrete vocabulary, uncovering both linguistic and paralinguistic patterns. Additionally, we explore the impact of clustering data selection on model robustness, highlighting the importance of domain matching between discretization training and target applications.

Voice conversion (VC) transforms source speech into a target voice by preserving the content. However, timbre information from the source speaker is inherently embedded in the content representations, causing significant timbre leakage and reducing similarity to the target speaker. To address this, we introduce a Universal Semantic Matching (USM) residual block to a content extractor. The residual block consists of two weighted branches: 1) universal semantic dictionary based Content Feature Re-expression (CFR) module, supplying timbre-free content representation. 2) skip connection to the original content layer, providing complementary fine-grained information. In the CFR module, each dictionary entry in the universal semantic dictionary represents a phoneme class, computed statistically using speech from multiple speakers, creating a stable, speaker-independent semantic set. We introduce a CFR method to obtain timbre-free content representations by expressing each content frame as a weighted linear combination of dictionary entries using corresponding phoneme posteriors as weights. Extensive experiments across various VC frameworks demonstrate that our approach effectively mitigates timbre leakage and significantly improves similarity to the target speaker.

The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction. Existing LMMs typically concatenate representation of modalities along the sequence dimension and feed them into a large language model (LLM) backbone. While sequence-dimension concatenation is straightforward for modality integration, it often relies heavily on large-scale data to learn modality alignments. In this paper, we aim to model the relationships between modalities more purposefully, thereby achieving more efficient and flexible modality alignments. To this end, we propose Stream-Omni, a large language-vision-speech model with efficient modality alignments, which can simultaneously support interactions under various modality combinations. Stream-Omni employs LLM as the backbone and aligns the vision and speech to the text based on their relationships. For vision that is semantically complementary to text, Stream-Omni uses sequence-dimension concatenation to achieve vision-text alignment. For speech that is semantically consistent with text, Stream-Omni introduces a CTC-based layer-dimension mapping to achieve speech-text alignment. In this way, Stream-Omni can achieve modality alignments with less data (especially speech), enabling the transfer of text capabilities to other modalities. Experiments on various benchmarks demonstrate that Stream-Omni achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks. Owing to the layer-dimensional mapping, Stream-Omni can simultaneously provide intermediate text outputs (such as ASR transcriptions and model responses) during speech interaction, offering users a comprehensive multimodal experience.

Speech-to-speech translation (S2ST) has been advanced with large language models (LLMs), which are fine-tuned on discrete speech units. In such approaches, modality adaptation from text to speech has been an issue. LLMs are trained on text-only data, which presents challenges to adapt them to speech modality with limited speech-to-speech data. To address the training difficulty, we propose scheduled interleaved speech--text training in this study. We use interleaved speech--text units instead of speech units during training, where aligned text tokens are interleaved at the word level. We gradually decrease the ratio of text as training progresses, to facilitate progressive modality adaptation from text to speech. We conduct experimental evaluations by fine-tuning LLaMA3.2-1B for S2ST on the CVSS dataset. We show that the proposed method consistently improves the translation performances, especially for languages with limited training data.

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and tasks. However, spoken dialogue systems still lag behind in terms of naturalness. They tend to produce robotic interactions, with issues such as slow response times, overly generic or cautious replies, and a lack of natural rhythm and fluid turn-taking. This shortcoming is largely due to the over-reliance on the traditional cascaded design, which involve separate, sequential components, as well as the use of text as an intermediate representation. This paper propose a real-time, textless spoken dialogue generation model (RTTL-DG) that aims to overcome these challenges. Our system enables fluid turn-taking and generates responses with minimal delay by processing streaming spoken conversation directly. Additionally, our model incorporates backchannels, filters, laughter, and other paralinguistic signals, which are often absent in cascaded dialogue systems, to create more natural and human-like interactions. The implementations and generated samples are available in our repository: https://github.com/mailong25/rts2s-dg

Recently, ``textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In this paper, we propose SLM and LLM Integration for spontaneous spoken Dialogue gEneration (SLIDE). Specifically, we first utilize an LLM to generate the textual content of spoken dialogue. Next, we convert the textual dialogues into phoneme sequences and use a two-tower transformer-based duration predictor to predict the duration of each phoneme. Finally, an SLM conditioned on the spoken phoneme sequences is used to vocalize the textual dialogue. Experimental results on the Fisher dataset demonstrate that our system can generate naturalistic spoken dialogue while maintaining high semantic coherence.

This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex capabilities allowing simultaneous speaking and listening. The paper also details the training process, including data preparation with synthesized dialogues and adjustments for real-time interaction. We also developed a platform to evaluate conversational fluency and response coherence in multi-turn dialogues. We hope the release of the report can contribute to the future development of spoken LLMs in Taiwanese Mandarin.