hlrc

#utterance

string text

---

#response

utterance utterance

---

uint32 result

/*

* This file is part of hlrc_server

*

* Copyright(c) sschulz <AT> techfak.uni-bielefeld.de

* http://opensource.cit-ec.de/projects/hlrc_server

*

* This file may be licensed under the terms of the

* GNU General Public License Version 3 (the ``GPL''),

* or (at your option) any later version.

*

* Software distributed under the License is distributed

* on an ``AS IS'' basis, WITHOUT WARRANTY OF ANY KIND, either

* express or implied. See the GPL for the specific language

* governing rights and limitations.

*

* You should have received a copy of the GPL along with this

* program. If not, go to http://www.gnu.org/licenses/gpl.html

* or write to the Free Software Foundation, Inc.,

* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.

*

* The development of this software was supported by the

* Excellence Cluster EXC 277 Cognitive Interaction Technology.

* The Excellence Cluster EXC 277 is a grant of the Deutsche

* Forschungsgemeinschaft (DFG) in the context of the German

* Excellence Initiative.

*

*/

#pragma once

#include "AudioData.h"

using namespace std;

using namespace hlrc_server;

#include "hlrc_server/phoneme.h"

#include "hlrc_server/soundchunk.h"

#include "hlrc_server/utterance.h"

#include "hlrc_server/ttsAction.h"

//converter from ros utterance

class UtteranceROS : public Utterance {

    public:

        UtteranceROS(ttsResultConstPtr ros_utterance){

            //set text:

            set_text(ros_utterance->utterance.text);

            //convert soundchunk to audio data:

            extract_audio_data(ros_utterance->utterance.audio);

            //convert phonemes:

            extract_phonemes(ros_utterance->utterance.phonemes);

        }

        ~UtteranceROS(){};

        void extract_audio_data(soundchunk sound_chunk){

            //extract data:

            unsigned int audio_len = sound_chunk.data.size();

            char *audio_data_char = (char *)sound_chunk.data.data();

            audio_data->samples.resize(audio_len);

            audio_data->samples.assign(audio_data_char, audio_data_char+audio_len);

            printf("audio samplesize is %d bytes\n",(unsigned int)audio_data->samples.size());

            /*

             * : data()

            , samplecount(0)

            , channels(0)

            , rate(0)

            , sample_type(0)

            , endianess(0)  {

            }*/

            //extract format:

            audio_data->sample_signed = true;

            switch (sound_chunk.sample_type){

                case(soundchunk::SAMPLE_U8):  audio_data->sample_signed = false; //and fall through:

                case(soundchunk::SAMPLE_S8):  audio_data->sample_bit =  8; break;

                case(soundchunk::SAMPLE_U16): audio_data->sample_signed = false; //and fall through:

                case(soundchunk::SAMPLE_S16): audio_data->sample_bit = 16; break;

                case(soundchunk::SAMPLE_U24): audio_data->sample_signed = false; //and fall through:

                case(soundchunk::SAMPLE_S24): audio_data->sample_bit = 24; break;

                default:

                    printf("> invalid sample type %d in ROS SoundChunk! ignoring request!\n", sound_chunk.sample_type);

                    throw runtime_error("UtteranceROS::convert_audio_data() unsupported sample type in ros SoundChunk");

            }

            //bitrate

            audio_data->sample_rate = sound_chunk.rate;

            //endianness

            if (sound_chunk.endianess == soundchunk::ENDIAN_LITTLE){

                audio_data->sample_big_endian = false;

            }else if (sound_chunk.endianess == soundchunk::ENDIAN_BIG){

                audio_data->sample_big_endian = true;

            }else{

                printf("> invalid SoundChunk byte_format");

                throw runtime_error("UtteranceROS::convert_audio_data() unsupported byte_format in ros SoundChunk");

            }

        //number of channels

        audio_data->sample_channels = sound_chunk.channels;

        printf("> new AudioData: %s\n",audio_data->to_string().c_str());

    }

    void extract_phonemes(utterance::_phonemes_type ros_phones){

        //extract phoneme vector

        phonemes_vector.clear();

        for(auto it = ros_phones.begin(); it<ros_phones.end(); it++){

            Utterance::symbol_duration_pair_t phoneme = make_pair(it->symbol, it->duration);

            phonemes_vector.push_back(phoneme);

        }

    }

};

#list of symbol/duration pairs

phoneme[] phonemes

#sound data (raw data, similar to a wave file)

soundchunk audio

#textual description

string text