今日论文合集：cs.SD语音1篇，eess.AS音频处理2篇。

cs.SD语音

【1】 Skit-S2I: An Indian Accented Speech to Intent dataset

标题：Skit-S2I：印度口音语音到意图的数据集

链接：https://arxiv.org/abs/2212.13015

作者：Shangeth Rajaa,Swaraj Dalmia,Kumarmanas Nethil
机构：Skit.ai, Bengaluru, India
摘要：传统的会话助手使用自动语音识别（ASR）从语音信号中提取文本转录，然后从转录中预测意图。使用端到端口语理解（SLU），说话者的意图直接从语音信号预测，而不需要中间文本转录。因此，该模型可以直接针对意图分类进行优化，并避免ASR的级联错误。端到端SLU系统还有助于减少意图预测模型的等待时间。尽管许多数据集对于文本转意图任务是公开可用的，但标记的语音转意图数据集的可用性是有限的，并且没有印度口音的数据集可用。在本文中，我们发布了Skit-S2 I数据集，这是银行领域中第一个以会话语气公开提供的印度口音SLU数据集。我们使用多个基线进行实验，比较了不同预训练语音编码器的表示，发现SSL预训练表示比缺乏韵律特征的ASR预训练表示在语音到意图分类方面性能略好。数据集和基线代码可从以下网址获得：\url{https：//github.com/skit-ai/speech-to-intent-dataset}
摘要：Conventional conversation assistants extract text transcripts from the speech signal using automatic speech recognition (ASR) and then predict intent from the transcriptions. Using end-to-end spoken language understanding (SLU), the intents of the speaker are predicted directly from the speech signal without requiring intermediate text transcripts. As a result, the model can optimize directly for intent classification and avoid cascading errors from ASR. The end-to-end SLU system also helps in reducing the latency of the intent prediction model. Although many datasets are available publicly for text-to-intent tasks, the availability of labeled speech-to-intent datasets is limited, and there are no datasets available in the Indian accent. In this paper, we release the Skit-S2I dataset, the first publicly available Indian-accented SLU dataset in the banking domain in a conversational tonality. We experiment with multiple baselines, compare different pretrained speech encoder's representations, and find that SSL pretrained representations perform slightly better than ASR pretrained representations lacking prosodic features for speech-to-intent classification. The dataset and baseline code is available at \url{https://github.com/skit-ai/speech-to-intent-dataset}


eess.AS音频处理

【1】 Blind estimation of room acoustic parameters from speech signals based  on extended model of room impulse response

标题：基于房间脉冲响应扩展模型的语音信号房间声学参数盲估计

链接：https://arxiv.org/abs/2212.13009

作者：Lijun Wang,Suradej Duangpummet,Masashi Unoki
机构：School of Information Science, Japan Advanced Institute of Science and Technology, -, Asashidai, Nomi, Ishikawa,-, Japan
备注：5-pages, 3 figures, 2 tables
摘要：语音传输指数（STI）和由房间脉冲响应（RIR）得到的房间声学参数（RAP）（例如混响时间和早期衰减时间）对于评估语音传输和预测声场中的听音困难是必不可少的。由于在日常占用空间中难以测量RIR，因此必须解决STI和RAP的同时盲估计，这是一个紧迫而具有挑战性的问题。本文基于一个近似未知RIR的RIR随机模型，提出了一种盲估计STI和5个RAP的确定性方法。该方法通过计算混响语音信号的时域功率包络来获得RIR模型的最优参数。进行仿真以评估来自所观察到的混响语音信号的STI和RAP。利用估计值与地面真实值之间的均方根误差对该方法与先前方法进行了比较评价。实验结果表明，该方法无需训练即可有效估计STI和RAP。
摘要：The speech transmission index (STI) and room acoustic parameters (RAPs), which are derived from a room impulse response (RIR), such as reverberation time and early decay time, are essential to assess speech transmission and to predict the listening difficulty in a sound field. Since it is difficult to measure RIR in daily occupied spaces, simultaneous blind estimation of STI and RAPs must be resolved as it is an imperative and challenging issue. This paper proposes a deterministic method for blindly estimating STI and five RAPs on the basis of an RIR stochastic model that approximates an unknown RIR. The proposed method formulates a temporal power envelope of a reverberant speech signal to obtain the optimal parameters for the RIR model. Simulations were conducted to evaluate STI and RAPs from observed reverberant speech signals. The root-mean-square errors between the estimated and ground-truth results were used to comparatively evaluate the proposed method with the previous method. The results showed that the proposed method can estimate STI and RAPs effectively without any training.


【2】 Skit-S2I: An Indian Accented Speech to Intent dataset

标题：Skit-S2I：印度口音语音到意图的数据集

链接：https://arxiv.org/abs/2212.13015

*与cs.SD语音【1】为同一篇

作者：Shangeth Rajaa,Swaraj Dalmia,Kumarmanas Nethil
机构：Skit.ai, Bengaluru, India
摘要：传统的会话助手使用自动语音识别（ASR）从语音信号中提取文本转录，然后从转录中预测意图。使用端到端口语理解（SLU），说话者的意图直接从语音信号预测，而不需要中间文本转录。因此，该模型可以直接针对意图分类进行优化，并避免ASR的级联错误。端到端SLU系统还有助于减少意图预测模型的等待时间。尽管许多数据集对于文本转意图任务是公开可用的，但标记的语音转意图数据集的可用性是有限的，并且没有印度口音的数据集可用。在本文中，我们发布了Skit-S2 I数据集，这是银行领域中第一个以会话语气公开提供的印度口音SLU数据集。我们使用多个基线进行实验，比较了不同预训练语音编码器的表示，发现SSL预训练表示比缺乏韵律特征的ASR预训练表示在语音到意图分类方面性能略好。数据集和基线代码可从以下网址获得：\url{https：//github.com/skit-ai/speech-to-intent-dataset}
摘要：Conventional conversation assistants extract text transcripts from the speech signal using automatic speech recognition (ASR) and then predict intent from the transcriptions. Using end-to-end spoken language understanding (SLU), the intents of the speaker are predicted directly from the speech signal without requiring intermediate text transcripts. As a result, the model can optimize directly for intent classification and avoid cascading errors from ASR. The end-to-end SLU system also helps in reducing the latency of the intent prediction model. Although many datasets are available publicly for text-to-intent tasks, the availability of labeled speech-to-intent datasets is limited, and there are no datasets available in the Indian accent. In this paper, we release the Skit-S2I dataset, the first publicly available Indian-accented SLU dataset in the banking domain in a conversational tonality. We experiment with multiple baselines, compare different pretrained speech encoder's representations, and find that SSL pretrained representations perform slightly better than ASR pretrained representations lacking prosodic features for speech-to-intent classification. The dataset and baseline code is available at \url{https://github.com/skit-ai/speech-to-intent-dataset}


机器翻译，仅供参考