Hasil Pencarian  ::  Simpan CSV :: Kembali

"Cross-word modeling for Arabic speech recognition utilizes phonological rules in order to model the cross-word problem, a merging of adjacent words in speech caused by continuous speech, to enhance the performance of continuous speech recognition systems. The author aims to provide an understanding of the cross-word problem and how it can be avoided, specifically focusing on Arabic phonology using an HHM-based classifier."

"

Salah satu permasalahan yang terdapat pada sistem Automatic Speech Recognition (ASR) yang sudah ada adalah kurangnya transparansi dalam penanganan data suara, yang tentunya membuat adanya keraguan terhadap privasi data tersebut. Di sisi lainnya, untuk mengembangkan sebuah sistem ASR yang memiliki akurasi memadai dan dapat bekerja secara luring membutuhkan jumlah data yang banyak, khususnya data suara yang sudah diiringi dengan transkripnya. Hal ini menjadi salah satu hambatan utama pengembangan sistem pengenalan suara, terutama pada yang memiliki sumber daya minim seperti Bahasa Indonesia. Oleh karena itu, dalam penelitian ini dilakukan perancangan sistem pengenalan suara otomatis berbasis model wav2vec 2.0, sebuah model kecerdasan buatan yang dapat mengenal sinyal suara dan mengubahnya menjadi teks dengan akurasi yang baik, meskipun hanya dilatih data dengan label yang berjumlah sedikit. Dari pengujian yang dilakukan dengan dataset Common Voice 8.0, model wav2vec 2.0 menghasilkan WER sebesar 25,96%, dua kali lebih baik dibandingkan dengan model Bidirectional LSTM biasa yang menghasilkan 50% namun membutuhkan jumlah data dengan label 5 kali lipat lebih banyak dalam proses pelatihan. Namun, model wav2vec membutuhkan sumber daya komputasi menggunakan 2 kali lebih banyak RAM dan 10 kali lebih banyak memori dibandingkan model LSTM

---

One of the main problems that have plagued ready-to-use Automatic Speech Recognition (ASR) Systems is that there is less transparency in handling the user’s voice data, that has raised concerns regarding the privacy of said data. On the other hand, developing an ASR system from scratch with good accuracy and can work offline requires a large amount of data, more specifically labeled voice data that has been transcribed. This becomes one of the main obstacles in speech recognition system development, especially in low-resourced languages where there is minimal data, such as Bahasa Indonesia. Based on that fact, this research conducts development of an automatic speech recognition system that is based on wav2vec 2.0, an Artificial Model that is known to recognize speech signals and convert it to text with great accuracy, even though it has only been trained with small amounts of labeled data. From the testing that was done using the Common Voice 8.0 dataset, the wav2vec 2.0 model produced a WER of 25,96%, which is twice as low as a traditional Bidirectional LSTM model that gave 50% WER, but required 5 times more labeled data in the training process. However, the wav2vec model requires more computational resource, which are 2 times more RAM and 10 times more storage than the LSTM model.

"

"Novel techniques for dialectal Arabic speech describes approaches to improve automatic speech recognition for dialectal Arabic. Since speech resources for dialectal Arabic speech recognition are very sparse, the authors describe how existing Modern Standard Arabic (MSA) speech data can be applied to dialectal Arabic speech recognition, while assuming that MSA is always a second language for all Arabic speakers. "

"Skripsi ini berisi tentang perbandingan dari 3 jenis algoritma VQ (Vector Quantization) yaitu Traditional K-Means Clustering, LBG (Linde, Buzo, and Gray), dan Sucessive Binary Split yang digunakan dalam proses pengenalan sinyal akustik (Suara) dari berbagai jenis ikan. Dalam proses pengenalan sinyal akustik ikan yang menggunakan HMM (Hidden Markov Model), sinyal akustik ikan yang akan dideteksi, terlebih dahulu dikuantisasi dengan menggunakan algoritma VQ.Pada sistem pengenalan sinyal akustik ikan, sinyal akustik ikan diubah terlebih dahulu ke dalam bentuk diskrit dengan cara sampling. Sinyal diskrit ini diekstraksi agar diperoleh karakteristiknya dengan menggunakan MFCC (Mel Frequency Cepstrum Coefficient). Vektor data yang terbentuk kemudian dikuantisasi dengan menggunakan 3 jenis algoritma VQ. Pada tahap pengenalan sinyal akustik ikan (recognition) yang memanfaatkan model HMM, ketiga jenis algoritma VQ ini diteliti unjuk kerjanya berdasarkan tingkat akurasi yang diperoleh.Berdasarkan hasil simulasi, algoritma Sucessive Binary Split merupakan algoritma paling optimum untuk sistem pengenalan sinyal akustik ikan karena memiliki tingkat akurasi tertinggi (pada ukuran codebook < 64) dengan kebutuhan kapasitas memori dan waktu komputasi (saat pembuatan codebook dan model HMM) paling kecil. Untuk memperoleh sistem pengenalan sinyal akuslik ikan dengan tingkat akurasi yang paling baik, algoritma LBG dapat digunakan dengan ukuran codebook > 128 tetapi kapasitas memori dan waktu komputasi yang dibutuhkan makin besar. Tingkat akurasi (recognition rate) pada sistem pengenalan sinyal akustik ikan yang menggunakan VQ dan HMM dapat ditingkatkan dengan memperbesar ukuran codebook, jumlah iterasi algoritma VQ, dan jumlah iterasi pada Baum Welch Algorithm."

"Build deep learning applications, such as computer vision, speech recognition, and chatbots, using frameworks such as TensorFlow and Keras. This book helps you to ramp up your practical know-how in a short period of time and focuses you on the domain, models, and algorithms required for deep learning applications. Deep Learning with Applications Using Python covers topics such as chatbots, natural language processing, and face and object recognition. The goal is to equip you with the concepts, techniques, and algorithm implementations needed to create programs capable of performing deep learning. This book covers intermediate and advanced levels of deep learning, including convolutional neural networks, recurrent neural networks, and multilayer perceptrons. It also discusses popular APIs such as IBM Watson, Microsoft Azure, and scikit-learn. You will: Work with various deep learning frameworks such as TensorFlow, Keras, and scikit-learn. Build face recognition and face detection capabilities Create speech-to-text and text-to-speech functionality Make chatbots using deep learning. "

"Extraction and representation of prosodic features for speech processing applications deals with prosody from speech processing point of view with topics including, the significance of prosody for speech processing applications, why prosody need to be incorporated in speech processing applications, and different methods for extraction and representation of prosody for applications such as speech synthesis, speaker recognition, language recognition and speech recognition."

"This book presents a contrastive linguistics study of Arabic and English for the dual purposes of improved language teaching and speech processing of Arabic via spectral analysis and neural networks. Contrastive linguistics is a field of linguistics which aims to compare the linguistic systems of two or more languages in order to ease the tasks of teaching, learning, and translation. The main focus of the present study is to treat the Arabic minimal syllable automatically to facilitate automatic speech processing in Arabic. It represents important reading for language learners and for linguists with an interest in Arabic and computational approaches."